© 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. 47267
    Prev
    Next
    INDEX
    Explanations

    Express. inn. product

    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
    t
    0.96
    Y
    0.79
    P
    0.73
    R
    0.72
    D
    0.71
    G
    0.69
    B
    0.67
    AJ
    0.66
    Kc
    0.66
    '
    0.65
    POSITIVE LOGITS
    ل
    0.89
    ール
    0.72
     Innocent
    0.63
    ين
    0.62
    訖
    0.61
    ый
    0.60
    е
    0.60
     የ
    0.60
     inns
    0.60
    逛
    0.58
    Activations Density 0.000%

    No Known Activations