© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 45754
    Prev
    Next
    INDEX
    Explanations

    yin and yang duality

    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_13_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
    r
    0.71
    ون
    0.62
    ร
    0.60
    s
    0.59
    réd
    0.56
    ور
    0.55
     هذا
    0.55
    晓
    0.55
    ر
    0.54
    {
    0.53
    POSITIVE LOGITS
     felonies
    0.62
     Threatened
    0.56
     SPEAK
    0.55
     knockout
    0.55
     EDUCATION
    0.55
     anarchy
    0.55
     mathematicians
    0.55
     guvern
    0.54
     felony
    0.54
     aerospace
    0.54
    Activations Density 0.005%

    No Known Activations