© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 81947
    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_0_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
    ت
    1.21
    ك
    1.05
    т
    1.01
    त
    0.99
    ing
    0.95
    ed
    0.92
    ri
    0.91
    w
    0.90
    ut
    0.86
    ro
    0.83
    POSITIVE LOGITS
    in
    0.88
    用
    0.64
    inase
    0.61
     Jackson
    0.58
    inah
    0.58
    し
    0.58
    がお
    0.58
    <0xE5>
    0.57
     IntelliJ
    0.57
    杷
    0.56
    Activations Density 0.000%

    No Known Activations