© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 33716
    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_40_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     Ciencias
    0.40
    𝚆
    0.39
     मॉडल
    0.38
    fprintf
    0.38
    飭
    0.38
     Modelle
    0.37
    cumsum
    0.37
    model
    0.36
    モデル
    0.36
     model
    0.36
    POSITIVE LOGITS
     $<\
    0.42
     speeds
    0.41
    ://
    0.39
    ):(
    0.38
    speed
    0.38
    ,/
    0.37
    Hyper
    0.37
    ylum
    0.37
     speed
    0.37
     aang
    0.37
    Activations Density 0.000%

    No Known Activations