© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    4. 12079
    Prev
    Next
    INDEX
    Explanations

    prevalence, prevalent, common, incidence

    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_13_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
    ી
    0.34
    op
    0.32
    ками
    0.29
    ре
    0.29
    рая
    0.29
    regulating
    0.27
    只想
    0.27
    રી
    0.27
    и
    0.27
    ру
    0.27
    POSITIVE LOGITS
    调制
    0.31
     afferma
    0.29
     نبی
    0.28
    Parser
    0.28
     tanpa
    0.28
    プト
    0.28
     duh
    0.28
     نیست
    0.27
     Parser
    0.27
     bebek
    0.27
    Activations Density 0.143%

    No Known Activations