© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 6047
    Prev
    Next
    INDEX
    Explanations

    text about the holy spirit, gifts, and calling from God

    oai_token-act-pair · gemini-2.0-flash

    code and foreign languages

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
     Holy
    -0.82
     Spirit
    -0.80
    Holy
    -0.77
    HOLY
    -0.74
    Spirit
    -0.66
    holy
    -0.66
     spirit
    -0.64
     HOLY
    -0.63
     Spirits
    -0.60
     holy
    -0.59
    POSITIVE LOGITS
     nakalista
    0.62
    帖最后由
    0.60
    interopRequire
    0.59
    StackNavigator
    0.59
     InputDecoration
    0.58
    
    0.57
    awaiter
    0.56
    classnames
    0.56
     useStyles
    0.55
    orianCalendar
    0.55
    Activations Density 0.087%

    No Known Activations