© 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. 58861
    Prev
    Next
    INDEX
    Explanations

    this is

    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
    k
    0.94
    X
    0.75
    J
    0.69
    ก
    0.69
    '+
    0.68
    ک
    0.65
    ppy
    0.63
    IN
    0.61
    po
    0.61
    c
    0.61
    POSITIVE LOGITS
    ные
    0.72
    ຶ
    0.67
     は
    0.64
     技術
    0.63
     требует
    0.61
    感じる
    0.61
     года
    0.59
    льную
    0.59
     presión
    0.59
     اللغة
    0.59
    Activations Density 0.004%

    No Known Activations