© 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-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 10033
    Prev
    Next
    INDEX
    Explanations

    Russian words and phrases probably related to programming/software development

    oai_token-act-pair · gemini-2.0-flash

    Code/multilingual

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     useStyles
    -0.81
     Roskov
    -0.78
    PhysRev
    -0.77
    riwal
    -0.75
    Hochspringen
    -0.75
    مصادر
    -0.72
    \{\\
    -0.71
    twimg
    -0.71
     Platon
    -0.70
    GEBURTSDATUM
    -0.69
    POSITIVE LOGITS
     industriels
    0.52
     industriales
    0.49
     domestiques
    0.48
     supérieurs
    0.47
     enfans
    0.47
     commerciales
    0.44
     идут
    0.44
     superiori
    0.43
     énergé
    0.43
     commerciaux
    0.43
    Activations Density 0.306%

    No Known Activations