© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 163236
    Prev
    Next
    INDEX
    Explanations

    JSON and file processing

    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_31_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
     pebble
    0.25
    Опера
    0.25
     شیع
    0.23
     তরফে
    0.23
    BetMap
    0.23
     pebbles
    0.23
     déchir
    0.23
     겨
    0.22
    +#
    0.22
    ႉ
    0.22
    POSITIVE LOGITS
     JSON
    0.31
    JSON
    0.27
    json
    0.25
     JsonResult
    0.25
     json
    0.24
    测试
    0.24
    arka
    0.23
    ارق
    0.23
     Tests
    0.23
     JSONArray
    0.23
    Activations Density 0.000%

    No Known Activations