© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 206876
    Prev
    Next
    INDEX
    Explanations

    limestone formations and features

    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_6_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
     Into
    1.08
    티
    1.06
    الس
    0.99
    ியில்
    0.98
    ogenous
    0.97
    ৯
    0.95
    about
    0.93
    យើង
    0.90
     يك
    0.90
    ólito
    0.90
    POSITIVE LOGITS
    st
    1.03
    ,
    0.90
    ם
    0.89
    сті
    0.85
     kinases
    0.82
     cumulative
    0.80
    мся
    0.80
    มี
    0.77
    (
    0.77
     deviation
    0.76
    Activations Density 0.000%

    No Known Activations