© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 231714
    Prev
    Next
    INDEX
    Explanations

    received

    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_6_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
    ב
    1.00
    ו
    0.98
    ாக
    0.95
    其他
    0.95
    את
    0.91
    ме
    0.88
    もの
    0.87
    ква
    0.85
    一緒に
    0.85
    ból
    0.84
    POSITIVE LOGITS
    arı
    1.29
     in
    1.16
    ot
    0.95
    <
    0.95
    {
    0.91
    rs
    0.89
    ;
    0.88
    ā
    0.88
    rl
    0.87
    don
    0.84
    Activations Density 0.004%

    No Known Activations