© 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. 50841
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    Т
    0.57
    Τ
    0.48
    noz
    0.48
     তখনও
    0.47
     सवारी
    0.47
    Лю
    0.46
    閭
    0.46
    সো
    0.46
     تحفظ
    0.46
    cosh
    0.46
    POSITIVE LOGITS
     Gegen
    0.49
     พูด
    0.48
     คง
    0.48
     materially
    0.46
     mostly
    0.45
     ตั้ง
    0.45
     ماين
    0.43
     же
    0.42
     bland
    0.42
     delusional
    0.42
    Activations Density 0.000%

    No Known Activations