© 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-3-4B-IT
    5. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 9608
    Prev
    Next
    INDEX
    Explanations

    assignment

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_25_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
    ?;
    0.74
    ;,
    0.73
     =
    0.71
     ‬
    0.68
    ;//
    0.67
     =,
    0.67
     დ
    0.66
     ='
    0.64
     Меди
    0.63
    
    0.63
    POSITIVE LOGITS
     Object
    0.93
    Object
    0.80
     JSON
    0.77
     decode
    0.77
     String
    0.74
    JSON
    0.74
     penetrate
    0.71
    Boolean
    0.70
    String
    0.69
     moment
    0.68
    Activations Density 0.050%

    No Known Activations