© 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. 10524
    Prev
    Next
    INDEX
    Explanations

    closed eyes

    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
     closed
    1.66
     закры
    1.63
     closing
    1.61
    闭
    1.59
     Closed
    1.55
     closes
    1.52
     closure
    1.50
    Closed
    1.50
     Closing
    1.50
    閉
    1.48
    POSITIVE LOGITS
     retiro
    0.41
     colorless
    0.40
     coef
    0.39
    bald
    0.39
    ἆ
    0.38
     uzak
    0.37
     undetectable
    0.37
    িল্লার
    0.37
     réfé
    0.37
     lontano
    0.36
    Activations Density 0.001%

    No Known Activations