© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 160562
    Prev
    Next
    INDEX
    Explanations

    gobierno

    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_2_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
    л
    0.70
    то
    0.62
     дітей
    0.61
    ми
    0.59
    ма
    0.55
    ിയ
    0.55
     усі
    0.55
     заболеваний
    0.55
    льше
    0.54
     мужчин
    0.54
    POSITIVE LOGITS
     be
    0.95
    ut
    0.88
    ul
    0.82
    in
    0.80
    w
    0.77
     a
    0.70
    un
    0.69
    od
    0.64
    ab
    0.62
    be
    0.61
    Activations Density 0.000%

    No Known Activations