© 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. 15134
    Prev
    Next
    INDEX
    Explanations

    the words 'cents', 'tax', and numbers near each other

    oai_token-act-pair · gemini-2.0-flash

    variations of the word "change"

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

    change (money)

    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
     Paglinawan
    -0.68
    Autoritní
    -0.65
     Annotated
    -0.58
    +#+#
    -0.56
     שוליים
    -0.55
     mères
    -0.54
    AddHtmlAttribute
    -0.53
     layering
    -0.53
    hematical
    -0.52
    WebServlet
    -0.52
    POSITIVE LOGITS
     change
    2.47
     Change
    2.27
    change
    2.23
    Change
    2.19
     CHANGE
    2.03
    CHANGE
    1.86
     changement
    1.58
     cambio
    1.56
     changes
    1.33
     changed
    1.27
    Activations Density 1.589%

    No Known Activations