© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 62260
    Prev
    Next
    INDEX
    Explanations

    thymus and thymidine

    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_11_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
    که
    0.61
    ровкой
    0.61
    始め
    0.58
     കൊണ്ട്
    0.54
    型の
    0.52
    で
    0.52
    ベクトル
    0.52
    テーブル
    0.51
    ناک
    0.51
    サイズの
    0.51
    POSITIVE LOGITS
    lig
    0.52
     gegevens
    0.51
     alimentaires
    0.51
    𝖙
    0.50
    <0xE9>
    0.50
    仙台
    0.49
    sen
    0.48
     inquirer
    0.48
     مواليد
    0.48
    𝐥
    0.48
    Activations Density 0.001%

    No Known Activations