© 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. 19-GEMMASCOPE-2-TRANSCODER-262K
    7. 210716
    Prev
    Next
    INDEX
    Explanations

    electron-positron pairs

    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_19_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
    ōn
    0.47
    ūn
    0.45
    ..");
    0.45
    ünde
    0.44
     Arten
    0.44
     demanding
    0.44
    ôt
    0.42
    িয়ার
    0.41
     allí
    0.41
     十分
    0.41
    POSITIVE LOGITS
     brillo
    0.47
     gloves
    0.46
    ），
    0.46
     biv
    0.44
    queros
    0.44
    𝑤
    0.44
    wk
    0.43
     globe
    0.43
    𝕨
    0.42
    KES
    0.42
    Activations Density 0.001%

    No Known Activations