© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 10311
    Prev
    Next
    INDEX
    Explanations

    physics and related fields

    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
    Negative Logits
     composition
    0.53
    地理
    0.50
    Composition
    0.50
    composition
    0.50
     Composition
    0.48
    composer
    0.47
     compositional
    0.47
     compositions
    0.46
     जियोग्राफी
    0.45
    法
    0.43
    POSITIVE LOGITS
     physicists
    0.66
     quantum
    0.65
     Quantum
    0.61
    quantum
    0.59
     physics
    0.56
     кван
    0.56
    Quantum
    0.56
     optics
    0.54
     वेव्स
    0.54
    量子
    0.54
    Activations Density 0.010%

    No Known Activations