© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26
    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 20-GEMMASCOPE-2-TRANSCODER-262K
    4. 211781
    Prev
    Next
    INDEX
    Explanations

    ```json[ {"token": "\"", "weight": 0.1}, {"token": "\n", "weight": 0.08}, {"token": ",", "weight": 0.07}, {"token": " ", "weight": 0.07}, {"token": "}", "weight": 0.06}, {"token": "{", "weight": 0.06}, {"token": "(", "weight": 0.06}, {"token": "'", "weight": 0.05}, {"token": ";", "weight": 0.05}, {"token": "]", "weight": 0.04}]```

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_20_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     मानो
    0.42
     RegExp
    0.41
    рабаты
    0.41
    芈
    0.40
     мэ
    0.40
     забруд
    0.40
     возрасте
    0.38
     делу
    0.38
     típus
    0.38
     Rhonda
    0.38
    POSITIVE LOGITS
    \#
    0.44
    越多
    0.40
    Model
    0.40
    خش
    0.39
    ören
    0.39
    Remaining
    0.38
    "><?=$
    0.38
    तेला
    0.38
     Using
    0.37
    ুলি
    0.37
    Activations Density 0.000%

    No Known Activations