© 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. 123049
    Prev
    Next
    INDEX
    Explanations

    prefrontal cortex

    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
    то
    0.71
     журнала
    0.71
    ক
    0.71
    یع
    0.70
     επίπε
    0.69
     authorizes
    0.68
     речи
    0.67
     آیات
    0.67
    すすめ
    0.66
     և
    0.65
    POSITIVE LOGITS
    rit
    0.76
    dir
    0.73
    dil
    0.72
    dur
    0.70
    ro
    0.68
    do
    0.66
    ellis
    0.66
    df
    0.64
     Kull
    0.64
    din
    0.63
    Activations Density 0.000%

    No Known Activations