© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 229592
    Prev
    Next
    INDEX
    Explanations

    country and place names

    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_6_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
    ك
    1.13
    ls
    0.98
    ar
    0.98
    el
    0.95
    at
    0.93
    ו
    0.92
    lardan
    0.91
    lan
    0.88
    cı
    0.88
    er
    0.87
    POSITIVE LOGITS
    ä
    1.02
    ۔
    0.96
    ви
    0.86
    <0x0D>
    0.83
     र
    0.80
    아
    0.79
    는
    0.78
    ว่า
    0.77
    ።
    0.77
    (
    0.77
    Activations Density 0.000%

    No Known Activations