© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 10707
    Prev
    Next
    INDEX
    Explanations

    mentions of God or a higher power and religious concepts such as calling or sacrifice

    oai_token-act-pair · gemini-2.0-flash

    Spirituality and purpose

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    出版年
    -0.82
    PreferredItem
    -0.79
     HasFactory
    -0.72
     BrowserModule
    -0.72
    AndEndTag
    -0.70
     AspNetCore
    -0.69
    FormTagHelper
    -0.66
    StructEnd
    -0.66
    expandindo
    -0.66
     Shakspeare
    -0.65
    POSITIVE LOGITS
    addGroup
    0.50
    SqlDataReader
    0.49
    もった
    0.47
    <bos>
    0.46
    S
    0.45
    M
    0.43
    ...
    0.43
    IAction
    0.42
     useStyles
    0.42
     perhatian
    0.42
    Activations Density 1.801%

    No Known Activations