© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 241940
    Prev
    Next
    INDEX
    Explanations

    at the heart of

    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_25_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
    illator
    0.40
    <0xB1>
    0.39
    ibile
    0.37
    etl
    0.36
    colare
    0.36
    ibles
    0.35
    म्मी
    0.34
    igg
    0.34
    זי
    0.34
    <0xBB>
    0.34
    POSITIVE LOGITS
    的一些
    0.42
     Wimbledon
    0.40
     very
    0.39
     Croatia
    0.39
    ஒரு
    0.38
     Consejo
    0.38
    बद्दल
    0.38
     Deportivo
    0.38
     Asociación
    0.38
    flowing
    0.38
    Activations Density 0.002%

    No Known Activations