© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 18263
    Prev
    Next
    INDEX
    Explanations

    toxins

    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_15_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
    看到
    0.61
     görür
    0.59
    数据显示
    0.57
    FOX
    0.54
     =
    0.54
    ían
    0.53
     دولار
    0.53
     знаний
    0.52
     服务
    0.52
    馁
    0.52
    POSITIVE LOGITS
     Egi
    0.49
     elucidate
    0.48
     refining
    0.46
     l
    0.46
     {
    0.46
     sanding
    0.45
     use
    0.45
    يء
    0.45
     ups
    0.45
     Ignite
    0.45
    Activations Density 0.003%

    No Known Activations