© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 39838
    Prev
    Next
    INDEX
    Explanations

    current density or frame

    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_3_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
    కు
    0.62
    in
    0.59
    un
    0.59
    i
    0.57
    ي
    0.55
    し
    0.55
    inje
    0.54
    出
    0.54
    用力
    0.52
    的
    0.52
    POSITIVE LOGITS
     current
    0.81
     for
    0.76
     corrente
    0.76
     CURRENT
    0.73
     stabilize
    0.68
     from
    0.68
     by
    0.65
     corriente
    0.64
    '
    0.64
    ING
    0.63
    Activations Density 0.003%

    No Known Activations