© 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. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 77463
    Prev
    Next
    INDEX
    Explanations

    explain the component

    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_29_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
     Either
    0.31
     যেদিন
    0.30
     பக
    0.29
     either
    0.29
     soạn
    0.28
    某一
    0.28
     Previous
    0.28
     सटीक
    0.28
    ೮
    0.28
     लेख
    0.27
    POSITIVE LOGITS
    清潔
    0.30
     membayar
    0.28
     उद्य
    0.27
    ま
    0.27
    ័
    0.27
     dissemin
    0.26
    드시
    0.26
    eV
    0.26
     ekst
    0.26
    lifting
    0.26
    Activations Density 0.010%

    No Known Activations