© 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. 134837
    Prev
    Next
    INDEX
    Explanations

    Gemini, Benny, Denali

    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
    н
    1.01
    ン
    1.01
    IN
    0.99
    UR
    0.98
    प
    0.95
     Existen
    0.94
    K
    0.93
    DAL
    0.93
     UBND
    0.93
     Моск
    0.91
    POSITIVE LOGITS
    و
    1.13
    '
    1.05
    :
    1.01
    ни
    0.99
    -
    0.98
    ون
    0.96
    いを
    0.95
    >
    0.92
    <0xB2>
    0.90
    <0x92>
    0.89
    Activations Density 0.000%

    No Known Activations