© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 11500
    Prev
    Next
    INDEX
    Explanations

    uses of the word "way" occurring with certain prepositions, articles, and pronouns

    oai_token-act-pair · gemini-2.0-flash

    say "way"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     ways
    -2.92
    Ways
    -2.64
     Ways
    -2.63
     WAYS
    -2.53
    ways
    -2.53
    Way
    -2.31
    WAYS
    -2.23
     Way
    -2.20
    way
    -2.19
    WAY
    -2.09
    POSITIVE LOGITS
     كومونز
    0.79
    ReusableCell
    0.72
     تانيه
    0.66
     TextInputType
    0.57
    ביוגרפיה
    0.55
     hObject
    0.54
    ьере
    0.54
    Jeografia
    0.53
    tallet
    0.52
    creativecommons
    0.50
    Activations Density 1.832%

    No Known Activations