© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 210283
    Prev
    Next
    INDEX
    Explanations

    repetition and repeating elements

    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_20_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
     all
    0.33
     obstacle
    0.31
    ingle
    0.28
     L
    0.28
     Ut
    0.28
     Ac
    0.27
      
    0.26
     Per
    0.26
    例
    0.26
     repeating
    0.26
    POSITIVE LOGITS
    ন্টে
    0.33
     służ
    0.32
    㴬
    0.30
     sierpnia
    0.29
     грошы
    0.29
     logika
    0.29
    原子炉
    0.28
     uiteindelijk
    0.28
    Ꭻ
    0.28
     اسرائیلی
    0.28
    Activations Density 0.008%

    No Known Activations