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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 10728
    Prev
    Next
    INDEX
    Explanations

    phrases related to religion or relationships, often in the context of a church or religious community.

    oai_token-act-pair · gemini-2.0-flash

    concepts related to witnessing in a religious context

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

    Christian testimony

    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
    expandindo
    -0.63
     виправивши
    -0.63
     جغرافيا
    -0.57
    حياته
    -0.56
     typelib
    -0.55
    DebuggerNonUser
    -0.55
    ंदीखरीदारी
    -0.54
    OGND
    -0.54
     AssemblyTitle
    -0.53
    StructEnd
    -0.53
    POSITIVE LOGITS
     witness
    0.63
    witness
    0.56
     testimony
    0.55
     legacy
    0.55
     witnessing
    0.54
     christ
    0.53
     witnesses
    0.52
     ministries
    0.50
     Diakses
    0.49
     Christ
    0.48
    Activations Density 1.136%

    No Known Activations