© 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. 163116
    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
    Coins
    0.35
     rik
    0.35
    ൦
    0.35
     रिचार्ज
    0.34
    productList
    0.34
     assertEquals
    0.34
    撞
    0.34
    books
    0.33
    unków
    0.33
     हिंदू
    0.33
    POSITIVE LOGITS
     troubled
    0.38
     單
    0.37
    idental
    0.36
     volont
    0.35
    abod
    0.35
    ération
    0.35
    ettet
    0.35
     WI
    0.35
    ENDED
    0.35
     berichtet
    0.34
    Activations Density 0.000%

    No Known Activations