© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 46730
    Prev
    Next
    INDEX
    Explanations

    Zendesk

    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
    Not in Any Lists

    No Comments

    Negative Logits
    mış
    0.84
    ﺭ
    0.75
     disponibilités
    0.74
    문의
    0.71
    ності
    0.70
     molécules
    0.69
    ل
    0.69
    ಬ್ಬಿಣ
    0.69
     моги
    0.68
    ллер
    0.68
    POSITIVE LOGITS
    (
    0.77
    -
    0.77
    an
    0.72
    ens
    0.70
    AN
    0.69
    You
    0.67
    ان
    0.66
    ,
    0.66
    that
    0.62
    That
    0.62
    Activations Density 0.000%

    No Known Activations