© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 158089
    Prev
    Next
    INDEX
    Explanations

    usual assumptions

    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_2_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
    ला
    1.35
    د
    1.29
    ص
    1.17
    ่
    1.16
    ها
    1.11
    ्य
    1.05
    ط
    1.04
    la
    1.03
    های
    1.03
    t
    1.02
    POSITIVE LOGITS
    к
    1.20
    ı
    0.96
    <0xF3>
    0.84
    ্প
    0.83
    ú
    0.80
     ماشینونو
    0.79
    ard
    0.78
     കുറ
    0.77
     .
    0.77
    ak
    0.76
    Activations Density 0.000%

    No Known Activations