© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 32013
    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_50_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
     Katie
    0.37
    梨
    0.37
    繋がり
    0.35
    otis
    0.35
    Katie
    0.35
    மன்
    0.34
     aas
    0.34
    淉
    0.34
     తి
    0.33
     slippery
    0.33
    POSITIVE LOGITS
     Vanderbilt
    0.40
     bump
    0.39
    sol
    0.39
    czeniu
    0.39
     ይሆ
    0.38
    bump
    0.38
    ége
    0.37
    TST
    0.37
    enzo
    0.37
    idene
    0.37
    Activations Density 0.000%

    No Known Activations