© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 11123
    Prev
    Next
    INDEX
    Explanations

    words related to religion or church

    oai_token-act-pair · gemini-2.0-flash

    Church context

    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
     religious
    -1.55
     pray
    -1.50
     theological
    -1.48
     prayed
    -1.48
     prayer
    -1.43
     Religious
    -1.41
     praying
    -1.41
    Religious
    -1.36
     religion
    -1.35
     prays
    -1.34
    POSITIVE LOGITS
    writeField
    0.56
    PreferredItem
    0.56
    ctest
    0.52
    ThroughAttribute
    0.52
    ConstraintMaker
    0.50
    umeur
    0.49
    MethodManager
    0.47
    UnsafeEnabled
    0.47
     Савезне
    0.47
     ujednoznacz
    0.47
    Activations Density 0.827%

    No Known Activations