© 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. 39850
    Prev
    Next
    INDEX
    Explanations

    William followed by a last name

    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
    an
    0.88
    t
    0.86
    s
    0.83
     subdue
    0.68
    ู
    0.67
    en
    0.65
    os
    0.65
    in
    0.64
    r
    0.64
    o
    0.64
    POSITIVE LOGITS
    異なる
    0.68
    них
    0.65
    ک
    0.65
    دهای
    0.63
    으로써
    0.62
     величи
    0.61
    大き
    0.61
    ılan
    0.61
    할
    0.61
    日程
    0.61
    Activations Density 0.000%

    No Known Activations