© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 126360
    Prev
    Next
    INDEX
    Explanations

    names of restaurants and people

    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_3_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
     is
    0.96
     has
    0.93
     sugar
    0.80
    '
    0.78
    k
    0.77
    ul
    0.73
    ka
    0.71
     to
    0.69
    te
    0.67
    ana
    0.67
    POSITIVE LOGITS
    BySize
    0.69
    אר
    0.68
    یک
    0.67
    ج
    0.66
    ၊
    0.65
    ).}
    0.65
    бы
    0.64
    이었
    0.63
    سازی
    0.63
    ньше
    0.61
    Activations Density 0.003%

    No Known Activations