© 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. 241791
    Prev
    Next
    INDEX
    Explanations

    function 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_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
     scru
    0.40
    ucian
    0.38
     cinética
    0.38
    祹
    0.37
     businessmen
    0.36
    γν
    0.36
     chasse
    0.36
     கொ
    0.35
    ්‍ය
    0.35
    曏
    0.35
    POSITIVE LOGITS
     bootstrap
    0.46
     Finished
    0.42
    .$(
    0.40
    Bootstrap
    0.38
     Bootstrap
    0.38
    étation
    0.38
    ளுடன்
    0.38
    Synchronization
    0.38
    ichtet
    0.36
    bj
    0.36
    Activations Density 0.001%

    No Known Activations