© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 9271
    Prev
    Next
    INDEX
    Explanations

    proper nouns and associated words related to European history and politics in the 1800s

    oai_token-act-pair · gemini-2.0-flash

    Great Britain

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    KommentareTeilen
    -0.56
    SequentialGroup
    -0.55
     getItemId
    -0.54
    存于互联网档案馆
    -0.53
    DBNull
    -0.48
     فل
    -0.47
    omiast
    -0.47
    chased
    -0.46
    ogel
    -0.46
     متعلقه
    -0.46
    POSITIVE LOGITS
    }))
    0.69
    ADELPHIA
    0.61
     pregunto
    0.60
    AllAfrica
    0.59
     dévelo
    0.58
     auroit
    0.58
     pouvoit
    0.58
     accro
    0.57
    Rujukan
    0.56
    addContainerGap
    0.56
    Activations Density 4.359%

    No Known Activations