© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 38827
    Prev
    Next
    INDEX
    Explanations

    iterate and collect

    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_11_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
    ip
    0.75
    n
    0.68
    u
    0.67
    os
    0.64
    ?
    0.62
    og
    0.59
    ру
    0.57
    ok
    0.56
    &
    0.56
    nice
    0.55
    POSITIVE LOGITS
    ,_-
    0.70
    সময়
    0.67
     vutt
    0.61
    <unused359>
    0.60
    <unused548>
    0.60
    <unused985>
    0.59
    లో
    0.57
    -{\
    0.57
    yyati
    0.56
    ベイ
    0.56
    Activations Density 0.011%

    No Known Activations