© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 60350
    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_11_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
    斯
    0.55
    伊
    0.55
    يب
    0.52
    انا
    0.52
    位于
    0.51
    न
    0.51
    器
    0.50
    文
    0.50
    اتب
    0.49
    若干
    0.49
    POSITIVE LOGITS
     filmy
    0.54
     iner
    0.48
     jis
    0.48
     decline
    0.47
     緊急
    0.47
     tk
    0.46
     filt
    0.46
     E
    0.46
     adapter
    0.46
     concili
    0.46
    Activations Density 0.000%

    No Known Activations