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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 5198
    Prev
    Next
    INDEX
    Explanations

    terms related to religion, specifically Mormonism

    oai_token-act-pair · gemini-2.0-flash

    Mormonism and religious beliefs

    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
    astify
    -0.69
    wpi
    -0.64
    +#+
    -0.64
    MigrationBuilder
    -0.64
     BorderSide
    -0.64
    bootstrapcdn
    -0.63
    TagMode
    -0.63
     LUMP
    -0.60
    wahati
    -0.59
     Union
    -0.56
    POSITIVE LOGITS
    Kanpo
    0.54
    Демографія
    0.50
    AddTagHelper
    0.49
     ویکی‌پدیای
    0.42
    IPT
    0.42
     divinely
    0.42
     Ramadan
    0.41
     faiths
    0.41
    }/${
    0.40
     Halal
    0.40
    Activations Density 6.421%

    No Known Activations