© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 57855
    Prev
    Next
    INDEX
    Explanations

    triceps

    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_2_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     و
    1.18
    дела
    0.99
     ו
    0.97
    мом
    0.97
     значение
    0.96
    لم
    0.96
     وي
    0.96
    وبي
    0.96
    А
    0.95
    انو
    0.95
    POSITIVE LOGITS
    다
    1.46
    し
    1.43
    :
    1.41
    ית
    1.35
    im
    1.32
    क
    1.32
    '
    1.24
    ↵
    1.23
    RE
    1.23
    س
    1.19
    Activations Density 0.001%

    No Known Activations