© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 211816
    Prev
    Next
    INDEX
    Explanations

    coroutine execution or sequential actions

    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_20_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
    Normalized
    0.44
     validator
    0.44
     /
    0.43
    Validator
    0.43
     endorsement
    0.43
     mathvariant
    0.42
    validated
    0.42
    treme
    0.42
    ELTS
    0.41
    nof
    0.41
    POSITIVE LOGITS
     אבל
    0.55
    但我
    0.50
    但
    0.48
     עם
    0.46
     但
    0.45
     pero
    0.44
    owntown
    0.44
     लेकिन
    0.43
    이지만
    0.43
     cosas
    0.43
    Activations Density 0.000%

    No Known Activations