© 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. 96317
    Prev
    Next
    INDEX
    Explanations

    Sonoran Desert

    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
    omás
    0.38
    álaga
    0.37
     relayed
    0.35
    લા
    0.34
    ക്കുറിച്ച്
    0.34
    <unused713>
    0.33
     લોકો
    0.32
    CLAS
    0.32
     غير
    0.32
     дистан
    0.32
    POSITIVE LOGITS
     dans
    0.40
     Proteins
    0.38
     Exxon
    0.38
     wy
    0.36
    ver
    0.36
    ברת
    0.36
     juc
    0.35
     Coronavirus
    0.35
    k
    0.35
    wy
    0.35
    Activations Density 0.001%

    No Known Activations