© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 125000
    Prev
    Next
    INDEX
    Explanations

    variable groups (R, X, Ar, n)

    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_37_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
     কাজী
    0.44
     System
    0.42
     Regardless
    0.39
     Expressions
    0.39
    System
    0.37
    Regardless
    0.36
    ２
    0.36
     outp
    0.36
     regardless
    0.36
    amentos
    0.36
    POSITIVE LOGITS
     молеку
    0.44
    氨
    0.39
    hess
    0.37
     بجائے
    0.37
    자인
    0.36
     უფ
    0.36
     priority
    0.36
    ঝো
    0.36
     mũi
    0.36
    itant
    0.35
    Activations Density 0.000%

    No Known Activations