© 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
    2. Gemma-3-27B-IT
    3. 39-GEMMASCOPE-2-TRANSCODER-262K
    4. 3886
    Prev
    Next
    INDEX
    Explanations

    maven repositories and imports

    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
     WE
    0.29
     milieux
    0.29
     दाल
    0.28
     dictionaries
    0.28
    QUA
    0.28
    字典
    0.27
     DHT
    0.27
    钉
    0.27
    QU
    0.26
    imidazol
    0.26
    POSITIVE LOGITS
     illuminates
    0.31
    gps
    0.30
     ornamental
    0.28
    gbm
    0.28
    眅
    0.28
     shudder
    0.28
    ApiCalls
    0.27
     obedience
    0.26
     effektiv
    0.26
    mathbb
    0.26
    Activations Density 0.001%

    No Known Activations