© 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-2-2B
    5. 2-GEMMASCOPE-TRANSCODER-16K
    7. 11310
    Prev
    Next
    INDEX
    Explanations

    mentions of God/Lord

    oai_token-act-pair · gemini-2.0-flash

    Lord

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     Lord
    -2.50
    Lord
    -2.31
     lord
    -2.11
     LORD
    -1.82
    LORD
    -1.64
    lord
    -1.59
     Lords
    -1.43
     lords
    -1.34
     Seigneur
    -1.17
     Señor
    -1.13
    POSITIVE LOGITS
     newBuilder
    0.58
     adal
    0.57
     oprot
    0.56
     дописавши
    0.54
     entière
    0.54
    Specification
    0.50
     Archiproducts
    0.50
    AsUp
    0.50
    onOptions
    0.48
     pulseira
    0.48
    Activations Density 0.611%

    No Known Activations