© 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. 2-GEMMASCOPE-2-TRANSCODER-16K
    7. 4073
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_2_width_16k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ра
    1.08
    Цена
    0.77
     Tek
    0.74
    $\\
    0.69
    теля
    0.69
    ানক
    0.68
    $.
    0.68
    ள்
    0.67
    Chúc
    0.67
    ЛЬ
    0.66
    POSITIVE LOGITS
    nement
    0.89
    startswith
    0.81
    ('.')[
    0.78
    ະ
    0.76
    lık
    0.76
    njih
    0.75
    eské
    0.74
    ürlich
    0.73
    lığ
    0.73
    ^{*},
    0.73
    Activations Density 0.755%

    No Known Activations