© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 139504
    Prev
    Next
    INDEX
    Explanations

    database tables

    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_37_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
     प्या
    0.42
     प्रमेय
    0.39
    执
    0.39
    執
    0.39
    mkdirs
    0.39
     liquides
    0.38
    LoggerFactory
    0.38
    ucalyptus
    0.37
    Foe
    0.37
    履
    0.37
    POSITIVE LOGITS
     database
    1.02
     databases
    0.94
     table
    0.94
     data
    0.90
    数据库
    0.87
    table
    0.86
     dataset
    0.86
     Database
    0.86
    data
    0.84
     Table
    0.84
    Activations Density 0.208%

    No Known Activations