© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 27868
    Prev
    Next
    INDEX
    Explanations

    QTableWidget

    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_40_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
     loudness
    0.43
    娅
    0.39
     জলের
    0.37
    鷗
    0.36
    鵲
    0.36
    珑
    0.36
     Louisa
    0.36
     Hackney
    0.36
    粼
    0.36
     unlock
    0.35
    POSITIVE LOGITS
    strat
    0.43
     Roles
    0.42
    iew
    0.39
    omy
    0.39
    personal
    0.39
    roles
    0.39
    progress
    0.39
    predictor
    0.38
    Plant
    0.38
    Roles
    0.37
    Activations Density 0.002%

    No Known Activations