© 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. 1958
    Prev
    Next
    INDEX
    Explanations

    positive sentiment and success-related terms in news reporting

    oai_token-act-pair · gemini-2.0-flash

    words related to winning or victory

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

    win

    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
     losing
    -0.65
     referenties
    -0.60
    MemoryWarning
    -0.57
     loosing
    -0.57
     lost
    -0.56
    losing
    -0.55
    lost
    -0.54
    HtmlAttribute
    -0.54
    awtextra
    -0.54
    ChildScrollView
    -0.54
    POSITIVE LOGITS
     win
    1.27
    win
    1.12
     wins
    1.00
     victory
    0.96
    Win
    0.96
     WIN
    0.95
    WIN
    0.94
     winnings
    0.89
     Win
    0.89
     gain
    0.87
    Activations Density 0.837%

    No Known Activations