© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 109317
    Prev
    Next
    INDEX
    Explanations

    expressed confidence

    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_1_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
     of
    0.93
    噙
    0.90
    。"
    0.87
     ofthe
    0.85
     我们
    0.84
    盽
    0.83
    浧
    0.80
    開催
    0.79
     bylo
    0.78
     që
    0.78
    POSITIVE LOGITS
    на
    1.66
    l
    1.63
    n
    1.47
    ni
    1.26
    na
    1.16
    ين
    1.11
    나
    1.09
    sa
    1.09
    ку
    1.08
    ल
    1.07
    Activations Density 0.002%

    No Known Activations