© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 6721
    Prev
    Next
    INDEX
    Explanations

    labels and captions for figures and tables in research papers

    oai_token-act-pair · gemini-2.0-flash

    scientific papers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    LogFactory
    -0.55
     arşivlendi
    -0.53
     незавершена
    -0.49
     them
    -0.47
    ContentAsync
    -0.44
    Décès
    -0.44
     they
    -0.44
    OfWork
    -0.43
     onItemClick
    -0.42
    Clik
    -0.42
    POSITIVE LOGITS
     Number
    0.74
     stället
    0.67
     Choice
    0.65
     Número
    0.63
    ngdoc
    0.62
     Relative
    0.61
    berdayakan
    0.60
     Cyclic
    0.60
     Anſ
    0.59
     Outer
    0.59
    Activations Density 14.078%

    No Known Activations