© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 15061
    Prev
    Next
    INDEX
    Explanations

    words related to medical testing and lab equipment, especially that made of plastic or metal.

    oai_token-act-pair · gemini-2.0-flash

    plastic

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
     steel
    -0.77
     plastic
    -0.75
     metal
    -0.64
     STEEL
    -0.63
    Plastic
    -0.60
     Steel
    -0.60
     Plastic
    -0.57
     plastique
    -0.56
    Steel
    -0.56
     metals
    -0.56
    POSITIVE LOGITS
    ]--;
    0.65
    ///</
    0.65
     cherchés
    0.64
    CodeAttribute
    0.64
    новниш
    0.64
    Hochspringen
    0.64
    Personendaten
    0.63
     ostavi
    0.62
    esez
    0.62
    AndEndTag
    0.61
    Activations Density 23.135%

    No Known Activations