© 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. 13425
    Prev
    Next
    INDEX
    Explanations

    mentions of churches and magnetic fields

    oai_token-act-pair · gemini-2.0-flash

    Church

    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
    ing
    -0.52
     Königreich
    -0.51
    setMaximum
    -0.50
     preventable
    -0.50
     poor
    -0.50
     avoidable
    -0.49
     advanced
    -0.49
    ).
    -0.49
     effectively
    -0.49
     check
    -0.48
    POSITIVE LOGITS
    SourceChecksum
    0.98
     '\\;'
    0.96
    SharedCtor
    0.94
    IntoConstraints
    0.90
    
    0.86
    Демографія
    0.85
    __':
    0.83
    BeginContext
    0.83
     autorytatywna
    0.81
    évaluateur
    0.80
    Activations Density 0.102%

    No Known Activations