© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 215307
    Prev
    Next
    INDEX
    Explanations

    numerical data

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
     ATL
    0.39
    ूज
    0.38
     উজ্জ
    0.38
    ETC
    0.38
     Beats
    0.38
    舏
    0.38
    khar
    0.37
    quipe
    0.37
    !(
    0.37
    aturation
    0.36
    POSITIVE LOGITS
    iyim
    0.41
    ยก
    0.41
     পূর্ণ
    0.39
    नेहा
    0.39
    íos
    0.39
    شا
    0.38
     شي
    0.38
    拋
    0.38
    ね
    0.38
     ยก
    0.37
    Activations Density 0.004%

    No Known Activations