© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 4253
    Prev
    Next
    INDEX
    Explanations

    concurrent execution

    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_39_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
     accidentes
    0.39
     గ్రా
    0.38
    Kab
    0.38
     cur
    0.37
     incompatibility
    0.36
     Villages
    0.36
    accio
    0.35
    ἥ
    0.35
     गाँव
    0.34
     ανε
    0.34
    POSITIVE LOGITS
     Executor
    0.47
     Execution
    0.45
     Cyclic
    0.45
     executions
    0.45
    Executor
    0.44
     Executors
    0.42
    EXECUT
    0.40
    TimeUnit
    0.40
    rejected
    0.40
     execution
    0.39
    Activations Density 0.004%

    No Known Activations