© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 74829
    Prev
    Next
    INDEX
    Explanations

    sorting alphabetically

    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_31_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    邑
    0.30
    zele
    0.29
     સંપ
    0.29
     sear
    0.28
     ASGI
    0.28
    Wesley
    0.27
     kapasitas
    0.27
    iberg
    0.27
    쐞
    0.27
    ambut
    0.27
    POSITIVE LOGITS
     dependencies
    0.32
    集体
    0.32
    mal
    0.31
     malfunctions
    0.31
     போ
    0.30
    頼
    0.30
     errors
    0.30
     মাল
    0.30
    úblic
    0.29
     companion
    0.29
    Activations Density 0.007%

    No Known Activations