© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 7190
    Prev
    Next
    INDEX
    Explanations

    text that references the Bible or Christian doctrine

    oai_token-act-pair · gemini-2.0-flash

    Religious/philosophical text

    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
    دانشنامهٔ
    -0.75
    sizeCache
    -0.69
     mourut
    -0.67
    Datuak
    -0.66
    
    -0.63
    ParallelGroup
    -0.63
     برانيه
    -0.62
     ModelExpression
    -0.61
    makeConstraints
    -0.61
     Erişim
    -0.60
    POSITIVE LOGITS
     participation
    0.49
     action
    0.47
    teryx
    0.46
    IsTrue
    0.45
    Criteria
    0.45
    INDU
    0.44
     miest
    0.43
     marcha
    0.43
    ąd
    0.43
    jusi
    0.41
    Activations Density 0.700%

    No Known Activations