© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 198276
    Prev
    Next
    INDEX
    Explanations

    fundamentals

    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
     core
    0.54
    core
    0.53
    核心
    0.50
     핵심
    0.50
    핵
    0.44
    घी
    0.38
    Core
    0.38
    的核心
    0.38
     Core
    0.38
     રી
    0.38
    POSITIVE LOGITS
    ทุก
    0.42
     Every
    0.39
     phoned
    0.38
    耐
    0.38
     Therap
    0.37
    Every
    0.36
     jusqu
    0.36
     %[
    0.36
    いは
    0.35
     Wednesdays
    0.35
    Activations Density 0.005%

    No Known Activations