© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 3394
    Prev
    Next
    INDEX
    Explanations

    run configuration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_39_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
     коды
    0.30
    чие
    0.29
     ਤ
    0.29
    ugen
    0.28
     relics
    0.28
     Б
    0.27
    coding
    0.27
     births
    0.27
    erness
    0.26
     brah
    0.26
    POSITIVE LOGITS
     TreeNode
    0.32
     undo
    0.27
    恂
    0.27
     Hous
    0.26
    ';",
    0.26
    馳
    0.25
    ihkan
    0.25
     ассоциа
    0.25
     Undo
    0.25
    勵
    0.24
    Activations Density 0.002%

    No Known Activations