© 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. 236816
    Prev
    Next
    INDEX
    Explanations

    execute/implement

    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
    glia
    0.41
    誡
    0.36
     umur
    0.35
    గిన
    0.34
    діть
    0.34
     النش
    0.34
     Systematic
    0.34
     litt
    0.33
     건
    0.33
     spacing
    0.33
    POSITIVE LOGITS
    执行
    1.19
    实施
    1.13
     execute
    1.08
     implement
    1.07
    Implement
    1.07
    implement
    1.07
     Implement
    1.05
     executes
    1.00
    執行
    0.99
     تنفيذ
    0.98
    Activations Density 0.001%

    No Known Activations