© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 35775
    Prev
    Next
    INDEX
    Explanations

    programming "final" declarations

    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_11_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
    to
    0.32
    us
    0.31
    as
    0.27
    ates
    0.25
    ដល់
    0.25
    k
    0.24
    sh
    0.24
    color
    0.23
    md
    0.23
    mw
    0.23
    POSITIVE LOGITS
     Steffen
    0.29
    ン
    0.29
    闵
    0.28
    燡
    0.27
     tae
    0.27
     Merseyside
    0.27
    WithFieldContext
    0.26
    壕
    0.26
     programme
    0.26
     Hackney
    0.26
    Activations Density 0.003%

    No Known Activations