© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 3262
    Prev
    Next
    INDEX
    Explanations

    dc. , os. , core. prefixes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_5_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
     بندی
    0.92
    ्य
    0.89
    مة
    0.87
    ме
    0.86
    пар
    0.85
     octobre
    0.82
    ত
    0.82
     buah
    0.81
    पंथी
    0.81
    ব
    0.81
    POSITIVE LOGITS
    Province
    1.00
     divalent
    1.00
    ર્ડ
    0.97
    Expense
    0.95
     pagos
    0.95
     respectivos
    0.93
     Biết
    0.91
     biết
    0.89
     enthalten
    0.88
     pihaknya
    0.87
    Activations Density 0.003%

    No Known Activations