© 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. 3996
    Prev
    Next
    INDEX
    Explanations

    references to books and chapters of the Bible, or more generally scriptural references

    oai_token-act-pair · gemini-2.0-flash

    scripture references or coding syntax

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

    books of the Bible

    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
     EconPapers
    -0.60
    SequentialGroup
    -0.60
    NameInMap
    -0.60
     &___
    -0.57
     кӀ
    -0.56
    riotic
    -0.49
    ⓧ
    -0.47
    MethodManager
    -0.45
     CanadaChoose
    -0.44
    elemField
    -0.44
    POSITIVE LOGITS
    endphp
    0.65
    TargetException
    0.55
    saraba
    0.54
    ticles
    0.52
     orar
    0.52
    _();
    0.51
    RTGC
    0.51
    RegressionTest
    0.50
    oquia
    0.50
    AFFIRMED
    0.50
    Activations Density 1.922%

    No Known Activations