© 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. 38-GEMMASCOPE-2-TRANSCODER-262K
    7. 5484
    Prev
    Next
    INDEX
    Explanations

    detecting code and programming keywords

    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_38_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
    ánto
    0.39
     winds
    0.39
    ඥ
    0.39
     People
    0.38
     Bible
    0.38
    Bir
    0.38
     funcionar
    0.38
     guns
    0.37
    ષ્ટ્ર
    0.37
     camisa
    0.37
    POSITIVE LOGITS
    interface
    0.61
     interface
    0.57
     interfaces
    0.54
     interfacing
    0.50
    ():
    0.49
     declare
    0.48
    (<
    0.47
    Interface
    0.46
     Interface
    0.46
     интерфей
    0.46
    Activations Density 0.012%

    No Known Activations