© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 124195
    Prev
    Next
    INDEX
    Explanations

    function and const declarations

    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
    ICATION
    0.45
     homepage
    0.41
    HomePage
    0.40
    首页
    0.39
    чности
    0.38
    طبيق
    0.38
    홈
    0.38
    cH
    0.37
    چر
    0.36
    せ
    0.36
    POSITIVE LOGITS
     Krebs
    0.39
    spac
    0.39
     Vit
    0.38
    ంతరం
    0.38
    jik
    0.36
    arounds
    0.35
    dater
    0.35
     Press
    0.35
    이다
    0.35
     Bruch
    0.35
    Activations Density 0.000%

    No Known Activations