© 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. 13620
    Prev
    Next
    INDEX
    Explanations

    text related to Mormon religious practices, beliefs, and organizations

    oai_token-act-pair · gemini-2.0-flash

    terms related to studies or research

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

    teaching/study

    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
    addCriterion
    -0.80
    principalColumn
    -0.78
    참고
    -0.73
     ModelExpression
    -0.68
    存于互联网档案馆
    -0.68
     bezeichneter
    -0.68
    CloseOperation
    -0.67
    quelize
    -0.65
     aveug
    -0.63
     newBuilder
    -0.63
    POSITIVE LOGITS
     study
    0.59
    study
    0.56
    rungsseite
    0.54
     units
    0.45
    journals
    0.45
     class
    0.44
    asius
    0.43
     record
    0.43
     Prasad
    0.41
     Study
    0.41
    Activations Density 2.006%

    No Known Activations