© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 136444
    Prev
    Next
    INDEX
    Explanations

    focus on formatting and preference

    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_12_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
    0.77
    i
    0.69
     -
    0.63
    ដែលមាន
    0.61
     που
    0.56
     ที่
    0.55
    ที่
    0.54
    Inventor
    0.54
    י
    0.54
    在
    0.54
    POSITIVE LOGITS
     Kardashians
    0.53
     subjecting
    0.48
     sequestration
    0.47
    मि
    0.46
    प्लिक
    0.46
    dtd
    0.46
     UCS
    0.46
     Basing
    0.46
    ヌ
    0.46
     composición
    0.46
    Activations Density 0.052%

    No Known Activations