© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 145357
    Prev
    Next
    INDEX
    Explanations

    提花揭示必需比較

    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_0_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
    er
    2.08
    ar
    1.93
    an
    1.73
    w
    1.73
    et
    1.68
    u
    1.65
    a
    1.59
    Y
    1.54
    U
    1.48
    ه
    1.47
    POSITIVE LOGITS
    ية
    1.31
    '
    1.21
    них
    1.06
    ের
    0.97
    вает
    0.95
     불구하고
    0.91
    को
    0.90
    กัน
    0.89
    ătoare
    0.89
    kenalkan
    0.88
    Activations Density 0.000%

    No Known Activations