© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 132130
    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_50_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
     ব্রিট
    0.39
     wing
    0.38
    тата
    0.37
     fallo
    0.37
     nightly
    0.37
    ሸ
    0.36
     tailings
    0.36
     wards
    0.36
    资金
    0.35
    ierend
    0.35
    POSITIVE LOGITS
    প্রা
    0.45
    鋼
    0.40
    BAT
    0.38
    FI
    0.38
    κ
    0.38
    side
    0.38
    भा
    0.37
     Ogden
    0.37
    zza
    0.37
     ខ
    0.37
    Activations Density 0.000%

    No Known Activations