© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 209412
    Prev
    Next
    INDEX
    Explanations

    home cook

    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_10_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
     rumah
    1.02
     मकान
    0.96
    home
    0.93
     خانه
    0.91
    at
    0.89
     HOME
    0.88
     dwellings
    0.88
    🏡
    0.88
    homes
    0.86
     dwellers
    0.86
    POSITIVE LOGITS
    s
    0.89
    。「
    0.73
    عين
    0.71
    I
    0.70
    지로
    0.69
    ()=>{
    0.69
    是
    0.68
    有
    0.67
    .。
    0.66
    ↵
    0.65
    Activations Density 0.010%

    No Known Activations