© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 11123
    Prev
    Next
    INDEX
    Explanations

    mentions of deities or expressions of gratitude

    oai_token-act-pair · gemini-2.0-flash

    References to God

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    -2.91
     god
    -2.86
    God
    -2.78
    god
    -2.53
     GOD
    -2.48
    GOD
    -2.28
     Gods
    -1.95
     gods
    -1.86
     Dios
    -1.83
     Dieu
    -1.81
    POSITIVE LOGITS
    onAttach
    0.72
    Cyfeiriadau
    0.61
    قایناقلار
    0.60
    Искәрмәләр
    0.55
     Roskov
    0.55
     חיצוניים
    0.54
     '\\;'
    0.50
    Билгалдахарш
    0.50
    ніципалі
    0.47
    Viited
    0.47
    Activations Density 1.374%

    No Known Activations