© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 137971
    Prev
    Next
    INDEX
    Explanations

    code and data

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
     Ка
    0.39
     Κα
    0.35
     கா
    0.34
     Kā
    0.33
     К
    0.33
     לג
    0.33
     Ку
    0.32
    牛奶
    0.32
     Kac
    0.31
    莺
    0.31
    POSITIVE LOGITS
    Lib
    0.35
    Pur
    0.34
    合理的
    0.34
     Versailles
    0.34
    Lips
    0.33
    NAL
    0.33
    Peru
    0.33
    Ral
    0.32
    ഉ
    0.32
     Pis
    0.32
    Activations Density 0.003%

    No Known Activations