© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 9-GEMMASCOPE-2-TRANSCODER-262K
    7. 193626
    Prev
    Next
    INDEX
    Explanations

    real time

    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_9_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
    s
    0.21
    ע
    0.19
    si
    0.19
    such
    0.19
    ss
    0.19
    pn
    0.18
    us
    0.18
    sites
    0.18
    ad
    0.17
    pw
    0.17
    POSITIVE LOGITS
    ジョン
    0.14
    <0x94>
    0.14
    कालिक
    0.14
     người
    0.13
    <0xA8>
    0.13
    <0xBB>
    0.13
     кеңсеси
    0.13
    ância
    0.13
     química
    0.13
    ovaná
    0.13
    Activations Density 0.069%

    No Known Activations