© 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. 9-GEMMASCOPE-2-TRANSCODER-262K
    7. 196204
    Prev
    Next
    INDEX
    Explanations

    trick

    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
    A
    0.88
    in
    0.79
    as
    0.75
     on
    0.75
    د
    0.75
    N
    0.72
    को
    0.71
    ana
    0.69
    d
    0.69
    Q
    0.68
    POSITIVE LOGITS
    త్మిక
    0.66
     tất
    0.60
    ?</
    0.58
    "};
    0.57
    עים
    0.55
    тет
    0.54
    ",[
    0.54
     dispositivi
    0.54
     esempl
    0.53
     edifici
    0.53
    Activations Density 0.002%

    No Known Activations