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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6227
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to God, faith, and religion

    oai_token-act-pair · gemini-2.0-flash

    references to God or divine guidance

    np_token-act-pair-logits · gpt-4o-mini

    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_21/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.21.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
    TypedDataSet
    -0.73
     '\\;'
    -0.66
    GEBURTSDATUM
    -0.65
     vectorielles
    -0.61
    MethodManager
    -0.58
    الإنجليزية
    -0.57
     vectorielle
    -0.55
     Sekund
    -0.54
     financières
    -0.52
    BoxLayout
    -0.52
    POSITIVE LOGITS
    pidou
    0.63
     invited
    0.54
    ijne
    0.51
    ApiProperty
    0.51
     HttpNotFound
    0.49
     share
    0.49
     pleased
    0.49
    ApiModelProperty
    0.48
    arXiv
    0.47
    simpleType
    0.46
    Activations Density 1.924%

    No Known Activations