© 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. 24789
    Prev
    Next
    INDEX
    Explanations

    much, much emphasis

    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
    OR
    0.95
    ED
    0.95
    u
    0.90
     Manganese
    0.85
    H
    0.85
    Y
    0.84
    č
    0.84
    Programa
    0.84
    O
    0.83
    Tanggal
    0.82
    POSITIVE LOGITS
    to
    0.87
    de
    0.75
    狈
    0.73
    ly
    0.72
     presenceData
    0.71
    𝗱
    0.70
     аре
    0.69
     серде
    0.69
     beauties
    0.68
     характеристи
    0.67
    Activations Density 0.048%

    No Known Activations