© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 163638
    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_31_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
    ‰
    0.39
     Annette
    0.35
    几乎
    0.35
    حه
    0.34
    幾乎
    0.34
    nce
    0.34
     almost
    0.34
     junt
    0.33
    
    0.33
    道歉
    0.33
    POSITIVE LOGITS
     TRANSM
    0.41
     следует
    0.40
     मुद्दों
    0.39
     Специа
    0.38
     ло
    0.38
     musicals
    0.38
    éma
    0.38
    ém
    0.37
     ആക
    0.37
     игр
    0.37
    Activations Density 0.000%

    No Known Activations