© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 210592
    Prev
    Next
    INDEX
    Explanations

    pure, followed by descriptor

    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_10_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
    و
    0.91
    ربی
    0.87
    صفر
    0.84
    ه‌
    0.83
    د
    0.82
    ی
    0.78
    ދ
    0.77
    ه‌های
    0.77
    وتر
    0.77
    два
    0.77
    POSITIVE LOGITS
    .
    1.09
    ,
    0.96
    </h2>
    0.91
    !
    0.89
    :
    0.88
    an
    0.88
     t
    0.86
    f
    0.86
     T
    0.85
    ne
    0.84
    Activations Density 0.003%

    No Known Activations