© 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. 2034
    Prev
    Next
    INDEX
    Explanations

    text discussing sewing, fashion, clothing, and fabric, with a particular emphasis on cost and the comparison between modern and historical practices.

    oai_token-act-pair · gemini-2.0-flash

    fashion-related terms

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

    fashion clothing

    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
    fjspx
    -0.78
    Portály
    -0.60
    URLException
    -0.57
    RegressionTest
    -0.56
    Frontier
    -0.50
    Saber
    -0.49
    NewGuid
    -0.49
    épa
    -0.49
     noDo
    -0.49
    Identyfik
    -0.49
    POSITIVE LOGITS
     fashion
    1.56
     clothing
    1.33
    fashion
    1.32
     Fashion
    1.29
    Fashion
    1.23
     clothes
    1.23
     Clothing
    1.19
     dress
    1.17
     moda
    1.15
     Clothes
    1.13
    Activations Density 2.604%

    No Known Activations