© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 142027
    Prev
    Next
    INDEX
    Explanations

    patrons

    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
    ك
    1.22
    ATING
    1.10
    䬲
    1.04
    す
    0.93
     கொண்ட
    0.91
    ธ์
    0.89
    )$;
    0.89
     чаще
    0.88
    ’
    0.88
     می‌شود
    0.87
    POSITIVE LOGITS
    is
    1.81
    i
    1.73
    es
    1.47
    ने
    1.47
    ra
    1.45
    т
    1.43
    ments
    1.38
    F
    1.38
    ت
    1.37
    it
    1.35
    Activations Density 0.000%

    No Known Activations