© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 197905
    Prev
    Next
    INDEX
    Explanations

    Lua keywords and syntax

    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_12_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
    from
    0.67
    with
    0.65
    Who
    0.63
    who
    0.61
    b
    0.60
    From
    0.59
    us
    0.56
    GOOD
    0.55
    FROM
    0.55
    eg
    0.55
    POSITIVE LOGITS
     utile
    0.57
     faible
    0.55
     ശേഷം
    0.54
     rejuvenating
    0.53
     getToken
    0.53
     président
    0.52
     പ്രച
    0.52
     আ
    0.52
     rousing
    0.52
    🌛
    0.52
    Activations Density 0.004%

    No Known Activations