© 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. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 51683
    Prev
    Next
    INDEX
    Explanations

    function return value

    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_30_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
     первич
    0.46
    widgetTo
    0.42
    緍
    0.38
    orderDetails
    0.37
     পোষ্ট
    0.37
     nameof
    0.37
     megy
    0.37
     کد
    0.36
    ್ದ
    0.36
    大道
    0.36
    POSITIVE LOGITS
     promised
    0.38
     pandas
    0.36
     enumer
    0.36
    ouin
    0.36
     է
    0.35
    が得
    0.35
     incubating
    0.34
    لام
    0.34
    rific
    0.34
    return
    0.34
    Activations Density 0.000%

    No Known Activations