© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 62611
    Prev
    Next
    INDEX
    Explanations

    rap battle

    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_11_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
    src
    0.51
    är
    0.50
    .,
    0.50
    im
    0.48
    ushing
    0.47
    gh
    0.46
    ../
    0.46
    llll
    0.46
    um
    0.45
    gl
    0.45
    POSITIVE LOGITS
    рует
    0.54
     Е
    0.52
    瓈
    0.52
    ние
    0.51
     韩
    0.51
     Han
    0.51
     chirp
    0.49
     なり
    0.48
    тива
    0.48
    parsedBlock
    0.48
    Activations Density 0.009%

    No Known Activations