© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 197214
    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_46_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
    рьох
    0.45
     роль
    0.43
     ontv
    0.41
    ➁
    0.40
    slf
    0.39
     ZF
    0.39
     imgs
    0.39
    镤
    0.38
     interrom
    0.38
     leop
    0.38
    POSITIVE LOGITS
    Which
    0.60
     Which
    0.59
    哪
    0.58
    Какие
    0.58
    哪些
    0.54
    有哪些
    0.54
    哪個
    0.53
    哪个
    0.53
    How
    0.52
     tips
    0.52
    Activations Density 0.000%

    No Known Activations