© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 168783
    Prev
    Next
    INDEX
    Explanations

    PRIMARY KEY, FOREIGN KEY

    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_34_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
     खल
    0.38
     soles
    0.37
     глу
    0.36
     resection
    0.36
    footer
    0.35
     আবার
    0.35
    馗
    0.35
     treated
    0.35
    treated
    0.35
    essential
    0.34
    POSITIVE LOGITS
     Moll
    0.38
    ナトリウム
    0.38
     Minkowski
    0.36
    细腻
    0.35
     Nessa
    0.35
     भरो
    0.35
    绵
    0.34
    予想
    0.34
     Drog
    0.33
     Predicted
    0.33
    Activations Density 0.000%

    No Known Activations