© 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-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 8906
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_3_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
    да
    3.28
    鹉
    2.54
    𝚕
    2.49
    
    2.47
    锢
    2.46
    𝑔
    2.46
    ch
    2.42
    াহিয়া
    2.38
     tendo
    2.35
    
    2.34
    POSITIVE LOGITS
    ी
    3.06
     неве
    2.76
     بندی
    2.73
    en
    2.72
    沓
    2.66
     RandomForest
    2.65
    います
    2.61
    ா
    2.60
     семьи
    2.59
    कालिक
    2.59
    Activations Density 0.078%

    No Known Activations