© 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. 88706
    Prev
    Next
    INDEX
    Explanations

    names and specific concepts like individualism

    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
    ي
    0.64
     been
    0.61
     воен
    0.58
     رئيس
    0.56
    را
    0.55
     سي
    0.55
    ással
    0.55
     дочери
    0.54
     the
    0.54
     ремонта
    0.53
    POSITIVE LOGITS
    t
    0.64
    ul
    0.59
    ไม่ใช่
    0.57
    이면
    0.57
    ون
    0.55
    کان
    0.54
    upl
    0.54
    ยิน
    0.54
    大
    0.54
    साठी
    0.52
    Activations Density 0.003%

    No Known Activations