© 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. 38343
    Prev
    Next
    INDEX
    Explanations

    Lady followed by name

    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
    в
    0.84
    し
    0.79
    حي
    0.75
    م
    0.74
    보
    0.74
    بي
    0.71
    hetes
    0.70
    的
    0.70
    ني
    0.69
    IO
    0.68
    POSITIVE LOGITS
    s
    0.80
    ی
    0.65
     것은
    0.60
     самую
    0.60
     разные
    0.59
     любую
    0.59
     зро
    0.56
     ιστο
    0.55
     дані
    0.55
     vague
    0.55
    Activations Density 0.003%

    No Known Activations