© 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. 43603
    Prev
    Next
    INDEX
    Explanations

    beautiful soup or destinations

    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
    ,
    0.98
    ING
    0.96
    1
    0.95
    ai
    0.91
    ش
    0.91
     the
    0.89
     is
    0.82
    ad
    0.81
     for
    0.80
     of
    0.79
    POSITIVE LOGITS
    ’)
    0.83
    לות
    0.80
    ‌هایی
    0.74
    려
    0.73
    لان
    0.72
    ！)
    0.72
    τή
    0.71
    ？）
    0.69
    لای
    0.69
    ‌های
    0.68
    Activations Density 0.006%

    No Known Activations