© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 213963
    Prev
    Next
    INDEX
    Explanations

    wan

    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_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
    ي
    1.13
    ز
    1.09
    си
    1.08
     μία
    1.04
    έ
    1.03
    "};
    1.00
    زي
    0.98
     estrellas
    0.94
    ៉
    0.93
     sanciones
    0.92
    POSITIVE LOGITS
    a
    1.13
    s
    1.05
    o
    1.03
    yta
    0.96
    y
    0.90
     a
    0.90
    as
    0.89
     .
    0.88
     was
    0.88
     беше
    0.87
    Activations Density 0.000%

    No Known Activations