© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 39009
    Prev
    Next
    INDEX
    Explanations

    Ruy Lopez and Live software

    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_3_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
     Fastest
    0.72
    ্রিক
    0.62
    お待ち
    0.62
    お
    0.62
    োড
    0.61
     Someone
    0.59
    }\
    0.59
    お届け
    0.59
    ೋಜನ
    0.59
    Screenshot
    0.58
    POSITIVE LOGITS
    ud
    0.93
    -
    0.87
    '
    0.86
    "
    0.73
    아
    0.71
     médica
    0.69
    های
    0.68
    ies
    0.67
    ب
    0.66
     that
    0.66
    Activations Density 0.004%

    No Known Activations