© 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-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 10313
    Prev
    Next
    INDEX
    Explanations

    set plot labels

    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_40_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
    AntiForgeryToken
    0.42
     cooperative
    0.41
     sofern
    0.38
     Wakefield
    0.37
     작성
    0.37
    Bod
    0.37
    errorCode
    0.36
     Cooperative
    0.36
    დაც
    0.35
    ˊ
    0.35
    POSITIVE LOGITS
    ጷ
    0.39
    ⿵
    0.38
    rela
    0.38
    rology
    0.37
    렉
    0.37
    推出
    0.36
    $\$
    0.36
    undu
    0.36
     нова
    0.36
    MEX
    0.36
    Activations Density 0.003%

    No Known Activations