© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 223875
    Prev
    Next
    INDEX
    Explanations

    rayon, song

    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_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
    t
    0.58
    懑
    0.52
    ევრი
    0.52
    轫
    0.52
    ুর
    0.50
    AMENTO
    0.50
    綘
    0.50
    ael
    0.49
     gravi
    0.49
    ிக்
    0.49
    POSITIVE LOGITS
    м
    0.59
     উদ্ভাব
    0.58
     буде
    0.55
    ه
    0.55
    MOND
    0.55
    textwidth
    0.53
    M
    0.53
     sarà
    0.53
     ทํา
    0.52
     خواهند
    0.52
    Activations Density 0.000%

    No Known Activations