© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 138306
    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_46_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     যৌথ
    0.36
     ①
    0.35
     wpt
    0.34
    lh
    0.33
    ouge
    0.33
    ①
    0.33
    <unused2115>
    0.33
     разве
    0.33
    ＃
    0.33
    வ்
    0.33
    POSITIVE LOGITS
     main
    0.39
    Main
    0.38
     mill
    0.36
    gers
    0.36
    ennes
    0.36
    Numer
    0.36
    reux
    0.35
    processing
    0.35
     Bibel
    0.34
    MILL
    0.34
    Activations Density 0.000%

    No Known Activations