© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 76191
    Prev
    Next
    INDEX
    Explanations

    function definition or brace checking

    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_31_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
    grocery
    0.35
    Countries
    0.33
    planet
    0.31
    USDA
    0.31
    Apollo
    0.30
    globin
    0.30
    饑
    0.30
    continental
    0.30
    stick
    0.30
    Harry
    0.30
    POSITIVE LOGITS
     Booking
    0.35
     어려
    0.33
     TOP
    0.33
    되었다
    0.32
    首先
    0.32
     O
    0.32
     Roc
    0.31
     首先
    0.31
     Jeong
    0.31
     debes
    0.31
    Activations Density 0.000%

    No Known Activations