© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 1626
    Prev
    Next
    INDEX
    Explanations

    the word "just", sometimes followed by other words indicating a state or behavior

    oai_token-act-pair · gemini-2.0-flash

    technical identifiers and programming terms

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

    just

    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
    Negative Logits
     just
    -2.98
    just
    -2.81
    Just
    -2.48
     Just
    -2.44
     JUST
    -2.11
     juste
    -2.08
    JUST
    -1.94
     simply
    -1.88
     juft
    -1.76
    simply
    -1.70
    POSITIVE LOGITS
    mybatisplus
    0.65
     resultCode
    0.52
     JADX
    0.47
    mnar
    0.45
    úcia
    0.43
    ähkö
    0.43
     оригіналу
    0.42
    ActionButton
    0.41
    Diwedd
    0.41
    findpost
    0.41
    Activations Density 0.498%

    No Known Activations