© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 2994
    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_5_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
     gini
    2.15
    ার
    2.08
     ১০
    2.05
    壑
    2.03
    
    1.97
     combien
    1.94
     ১৯৬
    1.93
    好き
    1.92
    anov
    1.92
     lakukan
    1.89
    POSITIVE LOGITS
    े
    2.06
    জন
    2.02
     retaining
    1.89
    тті
    1.80
    جا
    1.79
    case
    1.76
    on
    1.72
    ште
    1.68
     cont
    1.62
     retention
    1.62
    Activations Density 0.000%

    No Known Activations