© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 161955
    Prev
    Next
    INDEX
    Explanations

    foreign language prompts

    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_2_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
    くなる
    0.52
    rak
    0.49
    с
    0.46
    foot
    0.45
    )
    0.45
    اً
    0.45
    factory
    0.44
    action
    0.44
    ail
    0.43
    fiction
    0.43
    POSITIVE LOGITS
    ي
    0.77
    យើង
    0.50
    (
    0.49
    та
    0.49
    ير
    0.48
     legumes
    0.47
    {
    0.47
    nels
    0.46
     tablespoons
    0.45
     dashboards
    0.45
    Activations Density 0.003%

    No Known Activations