© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 49808
    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
     duration
    0.53
     durée
    0.50
     handler
    0.50
     langue
    0.43
    6
    0.42
    oven
    0.42
    æld
    0.42
     væ
    0.42
     Programme
    0.42
     packageName
    0.42
    POSITIVE LOGITS
    తో
    0.55
     Azte
    0.48
    їв
    0.47
    郆
    0.47
     profitably
    0.47
    ៉
    0.47
     ব্যবস
    0.47
    ၍
    0.46
     ஜெ
    0.46
     पुरात
    0.46
    Activations Density 0.000%

    No Known Activations