© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 33657
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_40_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
     fuss
    0.39
    face
    0.38
    sc
    0.37
    Supply
    0.37
    Server
    0.37
    lico
    0.37
    力
    0.37
    力的
    0.37
     Architects
    0.37
    lo
    0.37
    POSITIVE LOGITS
     نع
    0.38
    ្រី
    0.37
     Qualifying
    0.36
     наро
    0.36
     =========
    0.36
     озна
    0.36
    တာ
    0.36
     {{
    0.35
    ጠት
    0.35
     लगाना
    0.35
    Activations Density 0.000%

    No Known Activations