© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 1835
    Prev
    Next
    INDEX
    Explanations

    words related to war, conflict, and opposition

    oai_token-act-pair · gemini-2.0-flash

    fight

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     fight
    -2.39
     fighting
    -2.23
    fight
    -2.09
     Fight
    -2.05
     fights
    -2.03
     FIGHT
    -2.00
     fought
    -2.00
    Fight
    -1.97
    Fighting
    -1.95
    fighting
    -1.94
    POSITIVE LOGITS
    awtextra
    0.47
    Diwedd
    0.47
    
    0.45
     Wanna
    0.45
    ्वी
    0.45
     voulais
    0.45
    andu
    0.44
    ("]");
    0.44
     allons
    0.42
    orap
    0.42
    Activations Density 12.109%

    No Known Activations