© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 4863
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to Christianity, missions, and evangelism

    oai_token-act-pair · gemini-2.0-flash

    Christianity

    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
     doctrinal
    -0.60
     doctrine
    -0.58
     doctrines
    -0.55
     doctrina
    -0.51
     splitter
    -0.42
     Doctrine
    -0.42
    MethodImpl
    -0.42
     creeds
    -0.42
    greja
    -0.41
     creed
    -0.41
    POSITIVE LOGITS
    MigrationBuilder
    0.85
    complexContent
    0.82
    ChildScrollView
    0.78
     فريبيس
    0.78
    KommentareTeilen
    0.72
    adaptiveStyles
    0.71
    zzleHttp
    0.71
     Audiodateien
    0.70
     iprot
    0.69
    InputBorder
    0.69
    Activations Density 0.398%

    No Known Activations