© 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
    3. Gemma-3-27B-IT
    5. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 4208
    Prev
    Next
    INDEX
    Explanations

    lists of creative content types

    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
     internet
    0.32
    internet
    0.28
    ại
    0.28
     интернет
    0.28
    インターネット
    0.25
    ‍♀
    0.25
    web
    0.25
     rộng
    0.25
     الإنترنت
    0.24
    Internet
    0.24
    POSITIVE LOGITS
     unprotected
    0.26
    CNc
    0.23
    兢
    0.22
    พา
    0.22
     एलान
    0.21
     kammam
    0.21
     कराए
    0.21
     والا
    0.21
     ক্ষত্রিয়
    0.21
     تاہم
    0.21
    Activations Density 0.181%

    No Known Activations