© 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. 32038
    Prev
    Next
    INDEX
    Explanations

    complex tasks and reasoning

    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
    👬
    0.32
     konkre
    0.32
    👭
    0.29
    팍
    0.27
    🐵
    0.27
    परेट
    0.27
     চাচ
    0.27
    ূপ
    0.27
     ahuv
    0.27
    <\/
    0.26
    POSITIVE LOGITS
     복
    0.37
     Procedure
    0.32
     procedure
    0.30
     casual
    0.30
    procedure
    0.30
    華
    0.29
     Casual
    0.29
     prosedur
    0.29
     dragging
    0.28
    复杂
    0.28
    Activations Density 0.035%

    No Known Activations