© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 210338
    Prev
    Next
    INDEX
    Explanations

    ID, identifier

    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_10_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
    ി
    0.62
    ي
    0.61
    ু
    0.60
    ে
    0.58
    我
    0.55
    と
    0.54
    ために
    0.54
    ่
    0.54
    There
    0.54
     Imani
    0.53
    POSITIVE LOGITS
    able
    0.55
    of
    0.53
    >∕</
    0.52
    né
    0.52
    ierter
    0.51
    ți
    0.50
    ured
    0.50
    .
    0.49
    ł
    0.49
    uer
    0.49
    Activations Density 0.006%

    No Known Activations