© 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. 36324
    Prev
    Next
    INDEX
    Explanations

    North Atlantic, Pacific

    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
    ing
    0.66
    í
    0.66
    Ｉ
    0.63
    ó
    0.62
    Town
    0.61
     referência
    0.60
    li
    0.59
     vám
    0.59
    ري
    0.58
    ería
    0.58
    POSITIVE LOGITS
    ج
    0.91
    '
    0.78
    ने
    0.75
    어가
    0.74
    να
    0.74
    정을
    0.72
    عی
    0.72
    り
    0.67
    ческих
    0.67
    slateblue
    0.66
    Activations Density 0.000%

    No Known Activations