© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 198895
    Prev
    Next
    INDEX
    Explanations

    constantly

    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_4_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
     fluv
    0.64
    ל
    0.64
     realizzazione
    0.64
     შემთხვევაში
    0.59
     множество
    0.59
    rafa
    0.59
     barra
    0.59
     রেজিস্ট্র
    0.59
     wanton
    0.59
     νέα
    0.58
    POSITIVE LOGITS
    し
    0.80
    ন
    0.74
    h
    0.71
     in
    0.69
    น
    0.66
    นั่ง
    0.64
    r
    0.64
    an
    0.63
    ets
    0.61
    //*
    0.60
    Activations Density 0.127%

    No Known Activations