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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 144830
    Prev
    Next
    INDEX
    Explanations

    треугольник, распознавать, девятая

    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_0_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
    on
    1.69
     ре
    1.16
    ти
    1.16
    than
    1.14
     उपयोग
    1.12
    в
    1.10
     as
    1.09
     महत्व
    1.09
    not
    1.08
     бо
    1.08
    POSITIVE LOGITS
    -
    2.44
    কে
    1.83
    EN
    1.68
    ри
    1.65
     in
    1.41
    AL
    1.40
    :
    1.40
    '
    1.40
    ون
    1.37
    /
    1.36
    Activations Density 0.000%

    No Known Activations