© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 11878
    Prev
    Next
    INDEX
    Explanations

    titles associated with religious leaders and organizations

    oai_token-act-pair · gemini-2.0-flash

    titles related to religious leaders

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

    religious titles

    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
    twimg
    -0.57
     '\\;'
    -0.56
    stwie
    -0.53
    AddHtmlAttribute
    -0.52
    Diweddarwch
    -0.48
    
    -0.48
    AnchorStyles
    -0.47
    ]")]
    -0.46
    比亚
    -0.46
    "])
    -0.46
    POSITIVE LOGITS
     Rev
    1.73
    Rev
    1.61
     Reverend
    1.35
    Rever
    1.27
     pastor
    1.23
     Pastor
    1.22
     pastors
    1.16
    Pastor
    1.14
     reverend
    1.13
     REV
    1.10
    Activations Density 2.580%

    No Known Activations