© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 48486
    Prev
    Next
    INDEX
    Explanations

    U.S. Army Research

    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
    <unused379>
    0.73
    णीय
    0.71
     Poincaré
    0.71
    <unused1079>
    0.69
     ऑफ
    0.69
    poder
    0.69
    곸
    0.69
    <unused260>
    0.67
     Pelosi
    0.66
    <unused1062>
    0.66
    POSITIVE LOGITS
    ot
    0.66
    0.64
     December
    0.60
     fees
    0.60
     date
    0.57
    }.
    0.57
     fifties
    0.55
    .
    0.54
     waistcoat
    0.54
     notice
    0.53
    Activations Density 0.003%

    No Known Activations