© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 244540
    Prev
    Next
    INDEX
    Explanations

    finding min/max/shortest values

    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_40_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
    แห
    0.38
    多かった
    0.37
    ⾼
    0.37
    Flag
    0.36
    Bounding
    0.36
    앵
    0.36
    leer
    0.35
     ٻ
    0.35
    ViewSet
    0.34
    autoprefixer
    0.34
    POSITIVE LOGITS
     Broccoli
    0.39
    oum
    0.38
    ophyllum
    0.38
    istice
    0.37
     कुर्बानी
    0.37
    ([
    0.37
    oute
    0.36
    resents
    0.36
    ัพท์
    0.36
    нется
    0.36
    Activations Density 0.003%

    No Known Activations