© 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. 158190
    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
    ತೆ
    0.42
     takers
    0.40
    পে
    0.39
    hir
    0.39
     NO
    0.38
    丅
    0.38
    pizza
    0.38
    PointSize
    0.37
     ※
    0.37
    ؏
    0.37
    POSITIVE LOGITS
     Ras
    0.42
    년대
    0.39
     safe
    0.39
     SAFE
    0.39
    روف
    0.38
     Safe
    0.38
     ras
    0.38
     कॉमन
    0.38
     Commonwealth
    0.38
     CE
    0.38
    Activations Density 0.000%

    No Known Activations