© 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. 30800
    Prev
    Next
    INDEX
    Explanations

    .cpp files

    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
    িশ
    0.43
    ব্র
    0.42
     résist
    0.40
    ્ય
    0.40
     Moving
    0.40
     Locate
    0.39
     நாம
    0.39
    坵
    0.38
    舩
    0.38
    APAN
    0.38
    POSITIVE LOGITS
    ড়ন
    0.37
    cpp
    0.34
    脚本
    0.34
    opin
    0.33
    unbind
    0.33
    setFooter
    0.33
    function
    0.33
    こういう
    0.33
    ivy
    0.32
    llo
    0.32
    Activations Density 0.000%

    No Known Activations