© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 5205
    Prev
    Next
    INDEX
    Explanations

    words, phrases, and names related to Christian theology

    oai_token-act-pair · gemini-2.0-flash

    Religious context

    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
     artificiales
    -0.65
     programmation
    -0.60
     clínicos
    -0.56
     ControllerBase
    -0.53
     hans
    -0.52
     clínica
    -0.52
     civiles
    -0.52
     clinica
    -0.51
    hwnd
    -0.51
     pageContext
    -0.51
    POSITIVE LOGITS
    enumi
    0.52
    =?";
    0.51
     '\\;'
    0.50
    ()]);
    0.50
    Diweddarwch
    0.49
    irme
    0.49
    ↩
    0.49
    ----------
    0.48
    EndGlobalSection
    0.48
    whence
    0.46
    Activations Density 20.165%

    No Known Activations