© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 8261
    Prev
    Next
    INDEX
    Explanations

    words related to the body, particularly its anatomy, physiology, and illness

    oai_token-act-pair · gemini-2.0-flash

    keywords related to kidney function and health

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

    organs and related injury

    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
    談社
    -0.65
     Վերցված
    -0.54
    ramienta
    -0.52
     plomb
    -0.49
    raszamy
    -0.49
     sánh
    -0.49
     $__
    -0.48
    SelectedIndex
    -0.48
     समीक्षाओं
    -0.48
     Waldo
    -0.47
    POSITIVE LOGITS
    ]--;
    0.62
     MainAxisSize
    0.54
    PMailer
    0.52
    ]();
    0.52
    culin
    0.51
     BoxFit
    0.50
     ComVisible
    0.49
     кислота
    0.49
    lossians
    0.48
    AxisAlignment
    0.48
    Activations Density 3.359%

    No Known Activations