© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 142326
    Prev
    Next
    INDEX
    Explanations

    Wine compatibility layer

    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_12_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
    os
    0.57
    uette
    0.53
    <h2>
    0.52
     ث
    0.52
     resources
    0.50
    details
    0.50
     Liet
    0.50
    Ships
    0.50
    ,.
    0.50
    wires
    0.50
    POSITIVE LOGITS
     Según
    0.55
     ambientale
    0.55
     tenía
    0.54
     İz
    0.54
     Buck
    0.54
     pusieron
    0.53
    }):=\
    0.53
    ЕН
    0.52
     Pancake
    0.52
     Para
    0.52
    Activations Density 0.002%

    No Known Activations