© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 135443
    Prev
    Next
    INDEX
    Explanations

    involvement in

    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_1_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
    m
    2.58
    in
    2.14
    l
    2.09
    j
    1.82
    y
    1.79
    r
    1.70
    p
    1.69
    ul
    1.68
    م
    1.65
    re
    1.63
    POSITIVE LOGITS
     critic
    1.07
    жливо
    0.96
    cosity
    0.96
     helpline
    0.95
    databind
    0.95
    ぎ
    0.94
    gency
    0.93
     chakra
    0.93
     covalent
    0.92
    cadherin
    0.92
    Activations Density 0.001%

    No Known Activations