© 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
    2. Gemma-3-27B-IT
    3. 3-GEMMASCOPE-2-TRANSCODER-262K
    4. 36822
    Prev
    Next
    INDEX
    Explanations

    Paul Kagame, Paul Ehrlich, John Paul II

    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
     are
    0.80
    ן
    0.65
     about
    0.63
     does
    0.61
     includes
    0.61
     infecting
    0.60
     were
    0.60
    та
    0.60
    sı
    0.60
     occurred
    0.59
    POSITIVE LOGITS
     I
    0.73
    W
    0.66
    نا
    0.63
    。
    0.63
    ول
    0.61
    漯
    0.61
    I
    0.60
    ق
    0.59
     Bulg
    0.59
    ার্জ
    0.58
    Activations Density 0.002%

    No Known Activations