© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 1735
    Prev
    Next
    INDEX
    Explanations

    acknowledgements, addresses, and references in scientific papers

    oai_token-act-pair · gemini-2.0-flash

    non-standard symbols or formats

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

    Academic/research 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_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
    Negative Logits
     Studies
    -0.50
    kapet
    -0.50
     studies
    -0.50
     STUDY
    -0.49
    Населення
    -0.49
     studie
    -0.48
     STUDIES
    -0.47
     studied
    -0.47
    ViewFeatures
    -0.47
     étudier
    -0.46
    POSITIVE LOGITS
    IntoConstraints
    0.77
    GEBURTSDATUM
    0.70
     كومونز
    0.65
    SharedCtor
    0.63
    ChildScrollView
    0.63
    __*/
    0.62
     незавершена
    0.62
    nloa
    0.60
    DebuggerNonUser
    0.59
     lenker
    0.59
    Activations Density 2.028%

    No Known Activations