© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 9819
    Prev
    Next
    INDEX
    Explanations

    execution and implementation

    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_40_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
    ẹn
    0.38
    starts
    0.36
    mechanism
    0.35
    ertel
    0.35
     نظام
    0.34
    generator
    0.34
     מער
    0.34
    (-(
    0.33
    പ്പെട
    0.33
    िक्स
    0.33
    POSITIVE LOGITS
     execution
    2.47
     Execution
    2.25
     executed
    2.14
     execute
    2.08
    Execution
    2.08
    execution
    1.99
    执行
    1.98
     executing
    1.98
     executes
    1.91
     Execute
    1.87
    Activations Density 0.285%

    No Known Activations