© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 193355
    Prev
    Next
    INDEX
    Explanations

    json objects, comparing structured data

    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_4_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
    1
    0.73
    at
    0.71
    ia
    0.66
    ו
    0.64
     близько
    0.62
    はり
    0.61
     (
    0.61
    ad
    0.59
     {
    0.58
    ا
    0.58
    POSITIVE LOGITS
    馔
    0.77
    ną
    0.75
    ladı
    0.71
    栤
    0.71
    
    0.68
    arı
    0.68
    tų
    0.68
    tà
    0.67
    ن
    0.67
    டன்
    0.66
    Activations Density 0.000%

    No Known Activations