© 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. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 96292
    Prev
    Next
    INDEX
    Explanations

    sports teams and support

    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_14_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
     خرا
    0.56
    aternity
    0.55
     Kerala
    0.54
    त्सा
    0.53
    maan
    0.52
    avity
    0.52
    ity
    0.50
    z
    0.50
    د
    0.50
    udz
    0.50
    POSITIVE LOGITS
     Agregar
    0.54
     alemão
    0.53
     Bread
    0.53
     își
    0.50
     drugstore
    0.50
     Atom
    0.49
     lx
    0.49
     lb
    0.49
     CLICK
    0.49
     Toast
    0.48
    Activations Density 0.000%

    No Known Activations