© 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. 221704
    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
     없
    0.45
    ił
    0.44
    ابہ
    0.43
    ہوری
    0.43
     Eintrag
    0.42
     rechte
    0.42
     oczy
    0.42
     گ
    0.42
     გ
    0.41
     nỗi
    0.41
    POSITIVE LOGITS
    та
    0.52
     Cáceres
    0.49
    umbi
    0.48
     Carne
    0.47
    ﻊ
    0.46
    también
    0.46
     Namib
    0.46
     الأمريكي
    0.46
     rodean
    0.46
     विंड
    0.46
    Activations Density 0.000%

    No Known Activations