© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 13461
    Prev
    Next
    INDEX
    Explanations

    the phrase "in such a way"

    oai_token-act-pair · gemini-2.0-flash

    variations of the word "way"

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

    say "way" "manner" or "answer"

    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
     للمعارف
    -0.66
     كومونز
    -0.59
    twimg
    -0.57
    soka
    -0.57
    ẨM
    -0.54
     ligiloj
    -0.53
     שוליים
    -0.53
    offsetof
    -0.51
    XtraReports
    -0.50
    Kho
    -0.49
    POSITIVE LOGITS
     way
    3.33
    way
    2.50
    Way
    2.36
     Way
    2.31
     WAY
    2.30
     ways
    2.25
    WAY
    2.16
     manner
    2.08
    ways
    1.88
     façon
    1.82
    Activations Density 2.918%

    No Known Activations