© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-TRANSCODER-262K
    4. 51319
    Prev
    Next
    INDEX
    Explanations

    loop conditions with `< 5`

    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
    钊
    0.39
     يزيد
    0.31
    滑
    0.30
    मिताभ
    0.30
     ততক্ষণ
    0.30
    譞
    0.29
    滑动
    0.29
    ீர
    0.28
    なぜ
    0.28
     zaidi
    0.28
    POSITIVE LOGITS
    ః
    0.35
     Pire
    0.34
     Sev
    0.33
    ಃ
    0.32
     Brig
    0.32
    timber
    0.30
     timbers
    0.30
     introduced
    0.30
     Lanes
    0.29
     Hải
    0.29
    Activations Density 0.007%

    No Known Activations