© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 179953
    Prev
    Next
    INDEX
    Explanations

    non-Latin script

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
     espresso
    0.41
     berg
    0.40
    म्या
    0.39
     közö
    0.39
    猟
    0.38
     Berg
    0.37
     تجزی
    0.36
     turbo
    0.36
     wagons
    0.36
     Espresso
    0.35
    POSITIVE LOGITS
    राशि
    0.40
    aker
    0.40
    дию
    0.39
    habitat
    0.39
     शत्रु
    0.38
    archie
    0.38
    لاه
    0.38
     Mojo
    0.38
    akers
    0.38
    潛
    0.38
    Activations Density 0.000%

    No Known Activations