© 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. 102904
    Prev
    Next
    INDEX
    Explanations

    percentage signs and similar symbols

    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
    s
    1.41
    ;
    1.31
    m
    1.27
    k
    1.22
    >
    1.21
    },
    1.13
     H
    1.13
     I
    1.12
    v
    1.12
     R
    1.11
    POSITIVE LOGITS
    с
    1.36
    т
    1.31
    то
    1.23
    it
    1.22
    но
    1.18
    ו
    1.17
    й
    1.16
    い
    1.08
    ны
    1.04
    нави
    1.01
    Activations Density 0.001%

    No Known Activations