© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 90402
    Prev
    Next
    INDEX
    Explanations

    pygame.time.Clock()

    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_23_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
     seasonality
    0.45
    alal
    0.45
    \
    0.44
     ev
    0.42
     \%
    0.41
     lành
    0.41
     goc
    0.41
    变化的
    0.41
     uy
    0.40
    сійскай
    0.40
    POSITIVE LOGITS
     murderous
    0.47
     violently
    0.47
     fabricated
    0.46
    ография
    0.46
    ꒰
    0.45
     Graphics
    0.44
     созда
    0.43
     painfully
    0.43
     понимаю
    0.42
    adoras
    0.42
    Activations Density 0.000%

    No Known Activations