© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 876
    Prev
    Next
    INDEX
    Explanations

    numbers followed by commas

    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_39_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
     ratus
    0.42
     aden
    0.39
     bağlant
    0.39
    百
    0.38
    兟
    0.38
     vielen
    0.37
     saveData
    0.37
     ciencias
    0.37
     salón
    0.37
     büyük
    0.37
    POSITIVE LOGITS
    Comma
    0.49
     comma
    0.46
    comma
    0.43
    (",
    0.39
    {,}
    0.39
    [,
    0.37
     `,
    0.37
    _{,
    0.37
    srt
    0.36
    Intelligence
    0.36
    Activations Density 0.144%

    No Known Activations