© 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. 41-GEMMASCOPE-2-TRANSCODER-262K
    7. 64000
    Prev
    Next
    INDEX
    Explanations

    plot labels and markers

    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_41_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
     ales
    0.40
    羔
    0.39
     hả
    0.37
    못
    0.37
     Dirichlet
    0.35
    _/
    0.35
    的好
    0.34
    सिन
    0.34
     masu
    0.34
    㽞
    0.34
    POSITIVE LOGITS
    setAuto
    0.38
     Erlangen
    0.38
     автомобилей
    0.37
     Кита
    0.36
     осигурање
    0.36
     Фонбет
    0.36
    Smartphone
    0.35
    lagt
    0.35
    autoconfigure
    0.34
     objectForKey
    0.34
    Activations Density 0.001%

    No Known Activations