© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 47241
    Prev
    Next
    INDEX
    Explanations

    oahu

    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_10_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
     Vì
    0.59
    vì
    0.57
    failure
    0.57
     College
    0.56
    oodles
    0.56
    $=\
    0.55
    road
    0.54
    fighting
    0.54
    atlan
    0.53
    thern
    0.52
    POSITIVE LOGITS
    د
    0.61
     espada
    0.59
     suas
    0.57
    ¯</
    0.56
    珍
    0.55
    <0xE3>
    0.55
     internos
    0.54
     veditabbo
    0.54
    </td>
    0.53
     seu
    0.53
    Activations Density 0.005%

    No Known Activations