© 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. 102920
    Prev
    Next
    INDEX
    Explanations

    House or Congress

    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
    t
    1.16
    #
    1.05
    the
    0.97
    *
    0.93
    w
    0.93
    begin
    0.92
    中
    0.92
    at
    0.89
    O
    0.86
    name
    0.83
    POSITIVE LOGITS
    ের
    1.20
    ی
    1.07
    ्स
    1.02
     codons
    1.01
    og
    0.95
    aj
    0.94
    es
    0.93
     faucets
    0.92
     आईपीएस
    0.91
    ாக
    0.90
    Activations Density 0.000%

    No Known Activations