© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 88292
    Prev
    Next
    INDEX
    Explanations

    language, investment, net

    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_3_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
    دارة
    0.70
    t
    0.69
    لي
    0.63
    드
    0.62
    Ⲃ
    0.61
    지만
    0.61
     котором
    0.60
    دي
    0.58
    ுள்ளார்
    0.57
    금을
    0.57
    POSITIVE LOGITS
    ut
    0.89
    ু
    0.82
    ia
    0.79
    ’
    0.78
    ik
    0.76
    ا
    0.75
    ları
    0.73
    ha
    0.72
    1
    0.72
    ara
    0.71
    Activations Density 0.003%

    No Known Activations