© 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. 53381
    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
    🎏
    0.39
     Balkans
    0.35
    ার্থে
    0.33
    repl
    0.33
    总裁
    0.32
    📦
    0.32
    🥣
    0.32
     tuition
    0.32
     ഭാഗ
    0.32
    ábbi
    0.32
    POSITIVE LOGITS
     vineyard
    0.39
    頗
    0.38
    醋
    0.37
    Ridge
    0.36
     ridge
    0.36
     stating
    0.35
     ridges
    0.35
     identifiers
    0.35
    ofile
    0.34
     during
    0.34
    Activations Density 0.000%

    No Known Activations