© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 8119
    Prev
    Next
    INDEX
    Explanations

    the word "Holy" or words associated with religion

    oai_token-act-pair · gemini-2.0-flash

    Holy

    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
    pmc
    -0.48
    X
    -0.47
    ET
    -0.47
    is
    -0.43
    AI
    -0.43
    DP
    -0.42
    ip
    -0.42
    itra
    -0.42
    atch
    -0.41
    á
    -0.41
    POSITIVE LOGITS
     JpaRepository
    0.79
    rungsseite
    0.78
     سكانية
    0.75
    basicConfig
    0.75
     становника
    0.70
     ویکی‌پدی
    0.69
     Roskov
    0.69
     Wikispecies
    0.68
    ArgsConstructor
    0.68
     GeoNames
    0.68
    Activations Density 4.412%

    No Known Activations