© 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. 1696
    Prev
    Next
    INDEX
    Explanations

    text associated with biographical information and activism, especially peace activism

    oai_token-act-pair · gemini-2.0-flash

    words related to advocacy and activism

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

    fighting for change

    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
     Taktlose
    -0.62
    >{@
    -0.57
     StatelessWidget
    -0.47
    ArgumentParser
    -0.47
     OFDb
    -0.44
     ModelExpression
    -0.43
    Picking
    -0.43
     verwijzen
    -0.41
    Rich
    -0.40
     viss
    -0.40
    POSITIVE LOGITS
     advocating
    0.97
     advocacy
    0.96
    advoc
    0.93
     advocates
    0.92
     advocate
    0.90
     change
    0.82
     fight
    0.80
     Change
    0.80
     fighting
    0.79
    oa̍t
    0.79
    Activations Density 4.146%

    No Known Activations