© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 22368
    Prev
    Next
    INDEX
    Explanations

    posture

    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_56_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
    isek
    0.37
    谈判
    0.37
     उच्चारण
    0.36
    ሾ
    0.35
     dine
    0.34
    raquinone
    0.34
    cü
    0.34
     folio
    0.34
    俏
    0.34
    ా
    0.33
    POSITIVE LOGITS
     lying
    2.83
     laying
    2.33
    lying
    2.20
     лежа
    1.98
    laying
    1.88
     lig
    1.76
    躺
    1.70
     liegen
    1.66
     liggen
    1.62
     sitting
    1.59
    Activations Density 0.169%

    No Known Activations