© 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-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 13306
    Prev
    Next
    INDEX
    Explanations

    references to Christian religious texts and concepts

    oai_token-act-pair · gemini-2.0-flash

    Thessalonians

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     pleaſure
    -1.15
     Efq
    -1.11
     houſe
    -1.07
     Monfieur
    -1.05
     ſtate
    -1.04
    wiſe
    -1.02
     purpoſe
    -1.02
     Majefty
    -1.02
     Reſ
    -1.02
     Anſ
    -1.02
    POSITIVE LOGITS
    ↵↵
    0.77
    2
    0.59
    ↵
    0.58
      
    0.56
    1
    0.54
    4
    0.50
    7
    0.50
    lossians
    0.49
    B
    0.49
     
    0.48
    Activations Density 1.346%

    No Known Activations