© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 46044
    Prev
    Next
    INDEX
    Explanations

    sauce nuoc cham

    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_10_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
    Scenic
    0.75
    Geschichte
    0.72
    gning
    0.69
    ﺭ
    0.69
     الطاقة
    0.69
    Brightness
    0.68
    يف
    0.68
    برى
    0.68
    བྱ
    0.67
    é
    0.67
    POSITIVE LOGITS
     can
    1.05
     as
    1.03
    >
    0.89
     i
    0.88
    ik
    0.87
    .
    0.87
    ों
    0.87
    ς
    0.86
     to
    0.84
    ی
    0.84
    Activations Density 0.000%

    No Known Activations