© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 84343
    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_23_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
    cart
    0.49
     стрельца
    0.48
    s
    0.47
    m
    0.47
    infile
    0.46
    fwrite
    0.46
    %>%
    0.46
    اح
    0.46
    in
    0.45
    canny
    0.45
    POSITIVE LOGITS
     Vida
    0.50
     wider
    0.49
     larg
    0.47
     Essentials
    0.47
     япон
    0.47
     Vita
    0.46
     đẹp
    0.46
     fest
    0.45
    ↵↵↵↵↵↵↵↵
    0.44
     Trilogy
    0.44
    Activations Density 0.000%

    No Known Activations