© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 10156
    Prev
    Next
    INDEX
    Explanations

    argmax, argmin, argsort

    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_13_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
     мы
    0.12
    সমান
    0.12
    5
    0.12
    ถ่าย
    0.11
    Luther
    0.11
    Мы
    0.11
    鸹
    0.11
    )');
    0.11
    Reply
    0.11
    Smile
    0.11
    POSITIVE LOGITS
     prodotti
    0.12
     Appliances
    0.12
    ’
    0.12
     продукти
    0.11
    <0x81>
    0.11
     Cardiff
    0.11
     Đình
    0.11
     модер
    0.11
     Chevalier
    0.11
     McD
    0.11
    Activations Density 0.013%

    No Known Activations