© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 47235
    Prev
    Next
    INDEX
    Explanations

    closing parentheses or brackets

    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_13_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
    ä
    0.36
    ē
    0.34
    āna
    0.33
    )}(
    0.32
    ī
    0.31
     ت
    0.29
     إِل
    0.29
    )(
    0.28
    äär
    0.28
    är
    0.27
    POSITIVE LOGITS
    '
    0.34
    至於
    0.33
     Konzept
    0.32
    रूप
    0.30
    ských
    0.30
     VCO
    0.30
     Jen
    0.30
     Uc
    0.30
     Vid
    0.29
     Univer
    0.29
    Activations Density 0.038%

    No Known Activations