© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 37108
    Prev
    Next
    INDEX
    Explanations

    West, de, north, Southeast

    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_11_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
     subsequ
    0.53
    ות
    0.48
     bắt
    0.48
     thông
    0.48
     utiliz
    0.47
     isomorphisms
    0.47
     auf
    0.47
    と
    0.47
    
    0.47
     ה
    0.46
    POSITIVE LOGITS
    k
    0.56
    လူ
    0.55
     Jest
    0.50
    urban
    0.49
    цкий
    0.49
    ritable
    0.49
    simo
    0.49
    hene
    0.48
    燡
    0.48
    ermark
    0.47
    Activations Density 0.006%

    No Known Activations