© 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-3-4B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 259882
    Prev
    Next
    INDEX
    Explanations

    class implements interface

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_10_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
    陈
    0.77
    verwaltung
    0.72
    Various
    0.71
    experimental
    0.70
    services
    0.70
    Finder
    0.68
    various
    0.67
    정
    0.67
    analysis
    0.67
    또한
    0.66
    POSITIVE LOGITS
     Suppose
    0.87
     robbers
    0.79
     Très
    0.77
     ahorita
    0.77
     Уже
    0.76
    𝖎
    0.76
     initState
    0.76
     Bam
    0.76
     zigzag
    0.74
     bomber
    0.74
    Activations Density 0.000%

    No Known Activations