© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    4. 238814
    Prev
    Next
    INDEX
    Explanations

    inner/inside

    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_25_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
    thedocs
    0.42
    整備
    0.41
     насы
    0.39
    哌
    0.38
     ноябре
    0.38
     luar
    0.38
    ង់
    0.38
     बढ़ाने
    0.38
    óny
    0.38
     внешней
    0.38
    POSITIVE LOGITS
     Decorative
    0.40
    antu
    0.39
     Soud
    0.39
    iste
    0.39
    eks
    0.38
     Id
    0.37
     mythological
    0.37
    irond
    0.37
    \
    0.37
    Spl
    0.37
    Activations Density 0.003%

    No Known Activations