© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 88818
    Prev
    Next
    INDEX
    Explanations

    game mechanics and strategies

    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_11_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
    S
    0.62
    Gar
    0.61
     Disease
    0.59
    Disease
    0.57
    Bread
    0.56
    Child
    0.52
     Garbage
    0.52
    Have
    0.51
    Mar
    0.50
    Î
    0.50
    POSITIVE LOGITS
     chemot
    0.62
     bár
    0.61
     ventas
    0.60
     candidatos
    0.58
     dotyczą
    0.56
     tombol
    0.55
     ...)
    0.55
    چا
    0.55
     كومونز
    0.55
    。）
    0.53
    Activations Density 0.050%

    No Known Activations