© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 13523
    Prev
    Next
    INDEX
    Explanations

    words related to governments, people, and community

    oai_token-act-pair · gemini-2.0-flash

    politics and people

    np_max-act · gemini-2.0-flash

    people

    np_max-act-logits · gpt-5-mini
    Triggered by @chenshw0109
    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
    Negative Logits
     betweenstory
    -1.10
     Roskov
    -1.07
    InjectAttribute
    -1.04
     متعلقه
    -1.04
    تقاوى
    -1.02
     Majefty
    -0.97
     Efq
    -0.96
     ftate
    -0.96
     ſtate
    -0.95
     للاسماء
    -0.94
    POSITIVE LOGITS
    ↵↵
    0.81
    <eos>
    0.70
     
    0.69
     As
    0.66
     (
    0.66
     The
    0.66
    ↵
    0.66
     the
    0.65
     and
    0.62
    ,
    0.61
    Activations Density 1.863%

    No Known Activations