© 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. 44207
    Prev
    Next
    INDEX
    Explanations

    Italian names and places

    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
    ک
    0.89
    к
    0.85
    ۸
    0.81
    اسی
    0.81
    ม
    0.77
    ۶
    0.77
     to
    0.75
    н
    0.75
    м
    0.74
    ק
    0.73
    POSITIVE LOGITS
    ed
    0.88
    on
    0.78
    ar
    0.72
    r
    0.72
    es
    0.70
    ein
    0.70
    e
    0.70
    ogical
    0.70
    eing
    0.69
    al
    0.68
    Activations Density 0.000%

    No Known Activations