© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 125667
    Prev
    Next
    INDEX
    Explanations

    Prince names and places

    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
    ح
    0.73
    د
    0.70
    ?")
    0.68
    <h2>
    0.67
    ز
    0.66
    ام
    0.64
    д
    0.64
    手続き
    0.62
    ?)
    0.61
    ？）
    0.61
    POSITIVE LOGITS
    I
    0.83
    ’
    0.81
    '
    0.73
    V
    0.68
    S
    0.66
     zwią
    0.66
    O
    0.63
     sayıda
    0.63
    U
    0.63
    AV
    0.62
    Activations Density 0.000%

    No Known Activations