© 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. 50883
    Prev
    Next
    INDEX
    Explanations

    code syntax

    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
     atth
    0.32
    期間限定
    0.30
    %$$
    0.30
    कारण
    0.29
     yeast
    0.29
     सिन
    0.29
     çünkü
    0.28
    ப்பதற்கு
    0.28
     porque
    0.28
    >,</
    0.27
    POSITIVE LOGITS
    밀
    0.32
    しましたが
    0.30
    BUT
    0.30
     ווי
    0.30
     πλη
    0.29
     সম্পাদ
    0.29
     Ratio
    0.28
    Kol
    0.28
     Baw
    0.28
     Kol
    0.28
    Activations Density 0.046%

    No Known Activations