© 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. 127246
    Prev
    Next
    INDEX
    Explanations

    Eurovision song winner

    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
    с
    0.80
     are
    0.68
    ма
    0.66
     in
    0.65
    ки
    0.65
    ան
    0.64
    ра
    0.63
    դ
    0.61
    𝘀
    0.60
    ч
    0.60
    POSITIVE LOGITS
    i
    0.96
    A
    0.87
    a
    0.77
    I
    0.73
     poetic
    0.68
    y
    0.68
    o
    0.66
    with
    0.64
    ್
    0.63
    <
    0.63
    Activations Density 0.000%

    No Known Activations