© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 123727
    Prev
    Next
    INDEX
    Explanations

    gas mileage or Ideal Gas Law

    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_3_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
    at
    0.95
    ح
    0.82
    in
    0.77
    ع
    0.73
    人工智能
    0.71
    在
    0.71
    и
    0.69
    ص
    0.68
    一
    0.66
    ing
    0.66
    POSITIVE LOGITS
    AGUE
    0.66
    StillWater
    0.59
    PanelVisual
    0.57
    स
    0.54
    larghezza
    0.54
    וש
    0.52
    VARIABLES
    0.52
    Geometric
    0.52
     дат
    0.51
     enjoined
    0.51
    Activations Density 0.001%

    No Known Activations