google-deepmind/detectorscope
Build AI text detectors whose decisions are mechanistically grounded and human-auditable (EMNLP 2026)
Older snapshot: check the original source for current information.
From the publisher
README & documentation
Source previewRead the project’s overview, installation instructions and usage examples. The original README is the source of truth.
🔬 DetectorScope 🔬 AI text detectors that show their work. DetectorScope turns a black-box AI text detector into one whose every prediction is a sum of named, validated features. It can tell you which properties of a text made it predict "AI" and where in the text they are located. Try our demo! 🤗 https://huggingface.co/spaces/liamdugan/detector-scope-demo Using DetectorScope you can: The pipeline: SAEs on the detector's residual stream, a description and validation score per feature, a threshold on that score, and a sparse head over the features that pass. A DetectorScope detector is a concept bottleneck over interpretable sparse-autoencoder features: the language model's residual stream is encoded by SAEs, each feature gets a natural-language description that is validated against its own activations, and a sparse linear head over the validated features makes the decision. The prediction is therefore a sum of per-feature contributions, and every contribution has a description…
Read the full README ↗ · Preview checked 2026-10-29T12:35:27.694Z
Inside the original README — Document outline
- News
- Overview
- Results
- Installation
- Usage
- Models
- Reproducing the paper
- Citation
- Acknowledgements
- Disclaimer
- License
Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.
Links from the README
References supplied by the publisher, not independently verified endorsements. Check the destination before downloading files or entering credentials.
Documentation belongs to its respective authors. Reported project/model license: Apache-2.0. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.
What this repository does
Build AI text detectors whose decisions are mechanistically grounded and human-auditable (EMNLP 2026)
Repository facts
- Owner
- google-deepmind
- Primary language
- Python
- Stars
- 270
- Forks
- 23
- Open issues + pull requests
- 1
- License
- Apache-2.0
- Archived
- No
- Default branch
- main
- Created
- 2026-10-24T13:32:05.000Z
- Last push
- 2026-10-24T13:43:09.000Z
Topics and intended use
Owner-supplied topics: ai-text-detection, explainable-ai, interpretability, mechanistic-interpretability, sparse-autoencoders
Review the README for scope, installation, examples and limitations. We do not run repository code or certify it.
Evaluate before installing
Review licensing and dependencies, inspect recent commits and unresolved issues, and test in an isolated environment before production use. Stars and forks alone cannot answer these questions.
Source and freshness
Source: GitHub. Metadata observed 2026-10-30T12:16:30.730Z. Daily imports are snapshots, not real-time monitoring.
Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.
Related repositories
EbookFoundation/free-programming-books
donnemartin/system-design-primer