© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 241502
    Prev
    Next
    INDEX
    Explanations

    list formatting

    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_40_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
    .??
    0.38
    lds
    0.37
    rinth
    0.37
     मैट्र
    0.36
     stu
    0.36
    zoned
    0.35
    TH
    0.34
    یند
    0.34
    Ѕ
    0.34
    WD
    0.34
    POSITIVE LOGITS
     practised
    0.44
     practising
    0.41
     presently
    0.41
    KURZBESCHREIBUNG
    0.39
     Corbett
    0.39
    quered
    0.39
     دو
    0.39
     dip
    0.38
     Kommission
    0.38
     predicated
    0.37
    Activations Density 0.000%

    No Known Activations