© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 11971
    Prev
    Next
    INDEX
    Explanations

    instances of the word "force," particularly in the context of law enforcement, influence, or corporate power

    oai_token-act-pair · gemini-2.0-flash

    force

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    ,
    -0.99
    n
    -0.95
    .
    -0.94
     for
    -0.83
     at
    -0.78
     in
    -0.78
    ing
    -0.71
     
    -0.70
     on
    -0.70
     of
    -0.70
    POSITIVE LOGITS
     Theſe
    1.48
     itſelf
    1.29
     Beſ
    1.26
     ―――――
    1.23
    >\<^
    1.23
     ſeveral
    1.22
    ^(@)
    1.21
     doubtnut
    1.20
    NUMX
    1.20
     Anſ
    1.20
    Activations Density 2.197%

    No Known Activations