© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 139782
    Prev
    Next
    INDEX
    Explanations

    function calls and definitions

    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_37_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
    千里
    0.38
    듭
    0.38
    みたい
    0.36
     સંદ
    0.36
     להי
    0.35
    参考文献
    0.35
    implies
    0.35
    <unused304>
    0.35
    无穷
    0.34
     контек
    0.34
    POSITIVE LOGITS
     ()
    0.50
     ():
    0.44
    ()
    0.42
     callable
    0.41
     функцию
    0.40
     функ
    0.40
     func
    0.39
     fungsi
    0.39
     Module
    0.39
     funktion
    0.39
    Activations Density 0.001%

    No Known Activations