© 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. 128022
    Prev
    Next
    INDEX
    Explanations

    butter and bricks

    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
    ون
    0.86
    s
    0.81
    of
    0.80
    ำ
    0.70
    с
    0.69
    یل
    0.68
    as
    0.67
    ό
    0.67
    ๓
    0.66
    ан
    0.65
    POSITIVE LOGITS
    _
    0.72
    ua
    0.69
    iot
    0.65
    gette
    0.64
    ;
    0.63
    ktan
    0.62
    TI
    0.61
    ielle
    0.61
    '
    0.59
    voj
    0.57
    Activations Density 0.000%

    No Known Activations