© 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
    2. Gemma-3-27B-IT
    3. 23-GEMMASCOPE-2-TRANSCODER-262K
    4. 149053
    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_23_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
     没有
    0.53
     ಚಿತ್ರ
    0.46
     ಪ್ರಕಾರ
    0.46
     请
    0.45
     بالټ
    0.45
    变量
    0.44
     منظور
    0.44
     삭제
    0.43
     Вулкан
    0.43
     Consejo
    0.43
    POSITIVE LOGITS
     throughout
    0.49
     bookmarks
    0.48
     embroidered
    0.48
    тта
    0.46
     obič
    0.45
    कोर
    0.45
    ныгы
    0.45
    ي
    0.45
     från
    0.44
    ଦ
    0.44
    Activations Density 0.000%

    No Known Activations