© 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. 209867
    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
     ocorreu
    0.49
     SupCt
    0.48
    有無
    0.48
     configura
    0.47
    ).
    0.46
     módulos
    0.46
     [`
    0.46
     fudai
    0.46
     hypothalamic
    0.46
    .).
    0.45
    POSITIVE LOGITS
     كلكم
    0.52
    ו
    0.46
    ítás
    0.45
     الكل
    0.42
    icure
    0.42
    락
    0.41
    偪
    0.41
    اري
    0.40
    credi
    0.39
    문의
    0.39
    Activations Density 0.000%

    No Known Activations