© 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. 42802
    Prev
    Next
    INDEX
    Explanations

    Olympic Games or trees

    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
    '
    0.71
    )$
    0.66
    +"/"+
    0.66
    تری
    0.65
    )
    0.64
    ت
    0.64
    జేపీ
    0.63
    ット
    0.63
    ).\\
    0.62
    توان
    0.62
    POSITIVE LOGITS
    ir
    0.73
    rt
    0.73
    ور
    0.71
    o
    0.71
    in
    0.71
    ना
    0.69
    ell
    0.68
    ot
    0.68
    ul
    0.68
    all
    0.67
    Activations Density 0.000%

    No Known Activations