© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 80937
    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_31_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
    érées
    0.39
    jate
    0.38
    outes
    0.36
     nui
    0.36
     Herbs
    0.35
    搪
    0.35
    ונ
    0.35
    িল্প
    0.35
     carne
    0.35
     Waves
    0.35
    POSITIVE LOGITS
    Bez
    0.37
    佥
    0.37
     زي
    0.36
    တွ
    0.35
     desh
    0.33
     bez
    0.33
    札幌
    0.33
     stim
    0.33
    除去
    0.33
     Hippo
    0.33
    Activations Density 0.000%

    No Known Activations