© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 203540
    Prev
    Next
    INDEX
    Explanations

    mathematical operations

    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_6_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
    は
    0.79
    ের
    0.77
    은
    0.74
     can
    0.73
    ,【
    0.73
    -【
    0.72
    ా
    0.71
    %。
    0.70
     mexicanos
    0.70
     сдела
    0.69
    POSITIVE LOGITS
    ↵
    0.82
    .
    0.77
    u
    0.54
    TW
    0.54
    EL
    0.52
    OW
    0.52
            
    0.50
    wars
    0.50
    T
    0.50
    maze
    0.49
    Activations Density 0.002%

    No Known Activations