© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 136373
    Prev
    Next
    INDEX
    Explanations

    grains: rice, quinoa, oats, couscous

    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_12_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
    க்கே
    0.66
     Уен
    0.59
     ማስ
    0.56
     }}$,
    0.55
    новения
    0.55
    yyum
    0.55
    🍚
    0.55
     기름
    0.54
    _{+}\
    0.53
    ем
    0.53
    POSITIVE LOGITS
    ن
    0.55
    น
    0.53
    o
    0.52
    J
    0.52
    s
    0.50
    package
    0.48
    勬
    0.47
    aircraft
    0.46
    <0xEC>
    0.46
    0.46
    Activations Density 0.007%

    No Known Activations