© 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. 74765
    Prev
    Next
    INDEX
    Explanations

    in [place name]

    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
    钓
    0.32
     voglia
    0.31
    🐵
    0.30
     klub
    0.30
    ロッ
    0.29
     klubu
    0.29
    的那
    0.29
    ៈ
    0.29
     floating
    0.29
     बीबी
    0.29
    POSITIVE LOGITS
    between
    0.30
     खल
    0.30
    Escape
    0.29
    watches
    0.29
    drag
    0.29
     समाय
    0.29
    watch
    0.28
    Watch
    0.28
    ください
    0.28
    fence
    0.28
    Activations Density 0.001%

    No Known Activations