© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 226945
    Prev
    Next
    INDEX
    Explanations

    table

    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_6_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
    ى
    0.92
    ד
    0.88
    在
    0.87
    大
    0.86
    2
    0.85
     in
    0.82
    文件
    0.81
    し
    0.81
    ться
    0.80
    error
    0.79
    POSITIVE LOGITS
     \
    1.02
     THAT
    0.79
     reigning
    0.78
    ।"
    0.77
    that
    0.75
    ẫn
    0.74
     cią
    0.73
    ン
    0.72
     desarrollo
    0.71
     i
    0.71
    Activations Density 0.001%

    No Known Activations