© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 165194
    Prev
    Next
    INDEX
    Explanations

    loaded with

    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
    вање
    0.57
    ด
    0.57
    ч
    0.55
    ларга
    0.55
    rith
    0.54
    є
    0.54
    classlist
    0.52
    í
    0.51
    ␊
    0.50
     aula
    0.50
    POSITIVE LOGITS
     (__
    0.60
     by
    0.56
    X
    0.56
     congress
    0.54
     Congress
    0.52
     vx
    0.52
     our
    0.52
     process
    0.52
     vn
    0.52
     (
    0.52
    Activations Density 0.002%

    No Known Activations