© 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
    3. Gemma-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 8991
    Prev
    Next
    INDEX
    Explanations

    online discussions and guest blogging

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_3_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    в
    2.20
    м
    1.64
    lhs
    1.60
    ट
    1.58
    má
    1.56
    ι
    1.56
    .}$
    1.53
    த
    1.49
    .".
    1.49
    uf
    1.48
    POSITIVE LOGITS
     merchand
    1.57
     honours
    1.56
     overlapped
    1.56
     Mustangs
    1.52
    𝐀
    1.50
     prominently
    1.50
     대회
    1.47
    ඈ
    1.42
     honors
    1.42
     clashes
    1.41
    Activations Density 0.064%

    No Known Activations