© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 208956
    Prev
    Next
    INDEX
    Explanations

    well-formed parentheses and brackets

    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
    همه
    0.27
    აშ
    0.26
    ioon
    0.25
    拡散方程式
    0.24
    Resp
    0.24
    [...]
    0.24
    境
    0.24
    यन
    0.24
    chon
    0.23
    brightness
    0.23
    POSITIVE LOGITS
     k
    0.32
     pneum
    0.31
     Pennsylvania
    0.29
     Bike
    0.27
     tattoo
    0.27
     цикл
    0.27
     Credit
    0.27
     General
    0.26
     Ar
    0.26
     Non
    0.26
    Activations Density 0.001%

    No Known Activations