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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 19-GEMMASCOPE-TRANSCODER-16K
    7. 6625
    Prev
    Next
    INDEX
    Explanations

    words related to religion and faith, especially Christianity

    oai_token-act-pair · gemini-2.0-flash

    grace

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     Numerade
    -0.91
    脚注の使い方
    -0.88
    istoitu
    -0.87
     referenties
    -0.83
    AndEndTag
    -0.81
    OGND
    -0.81
     فريبيس
    -0.80
    存于互联网档案馆
    -0.77
    setVerticalGroup
    -0.77
    GEBURTSDATUM
    -0.76
    POSITIVE LOGITS
     grace
    0.87
    Grace
    0.75
     Grace
    0.73
    grace
    0.69
     GRACE
    0.65
    GRACE
    0.58
    sola
    0.48
    mai
    0.45
     works
    0.44
    text
    0.43
    Activations Density 1.135%

    No Known Activations