© 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. 8812
    Prev
    Next
    INDEX
    Explanations

    uses of the words "that," "this," and "way."

    oai_token-act-pair · gemini-2.0-flash

    instances of the word "way"

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

    Direction

    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
    Становништво
    -0.68
    ביוגרפיה
    -0.66
    новниш
    -0.65
     ivelany
    -0.59
     AssemblyCulture
    -0.57
    twimg
    -0.56
    principalColumn
    -0.56
     насељу
    -0.56
    LabelTagHelper
    -0.56
    Portale
    -0.55
    POSITIVE LOGITS
     way
    3.67
    way
    2.75
    Way
    2.66
     Way
    2.52
     WAY
    2.48
     ways
    2.38
    WAY
    2.38
    ways
    1.95
    Ways
    1.78
     Ways
    1.77
    Activations Density 1.636%

    No Known Activations