© 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. 18721
    Prev
    Next
    INDEX
    Explanations

    leader or chief

    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
    Serv
    0.39
    盒
    0.39
    Modifier
    0.38
    Tit
    0.37
    文件夹
    0.37
    folder
    0.36
    gender
    0.36
    Gender
    0.36
    奪
    0.36
    Boris
    0.35
    POSITIVE LOGITS
     trưởng
    0.94
    长的
    0.91
    長的
    0.88
    長の
    0.80
    長
    0.80
    长
    0.79
    장이
    0.74
    장은
    0.68
     chief
    0.64
    chief
    0.63
    Activations Density 0.007%

    No Known Activations