© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 108863
    Prev
    Next
    INDEX
    Explanations

    Específicas, específico

    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_1_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
    '
    2.00
    कर
    1.28
    ри
    1.04
    ка
    0.97
    री
    0.96
    ან
    0.96
    y
    0.96
    ру
    0.95
    ற்று
    0.93
    <0x80>
    0.91
    POSITIVE LOGITS
    ్‌
    1.00
    ین
    0.94
    ್ಟ
    0.93
    ა
    0.93
    9
    0.88
     فایل
    0.88
     وعرف
    0.85
    ্প
    0.83
    $;
    0.83
    ákat
    0.81
    Activations Density 0.000%

    No Known Activations