© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10500
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to God and religion

    oai_token-act-pair · gemini-2.0-flash

    God and religion

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     God
    -1.98
    God
    -1.80
     god
    -1.57
     GOD
    -1.39
    god
    -1.38
     Dios
    -1.31
    GOD
    -1.26
     Dieu
    -1.22
     Deus
    -1.11
    Dios
    -1.09
    POSITIVE LOGITS
    fieldId
    0.58
     AssemblyProduct
    0.58
     himo
    0.57
     صوتيه
    0.54
     sitter
    0.54
    delwed
    0.52
    ">—
    0.52
     Muda
    0.51
    затор
    0.50
     flam
    0.50
    Activations Density 1.094%

    No Known Activations