© 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. 3360
    Prev
    Next
    INDEX
    Explanations

    the word "domestic" along with words that sometimes occur near it, such as expenses, law, fights, and trade wars

    oai_token-act-pair · gemini-2.0-flash

    domestic

    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
    '
    -0.71
    er
    -0.66
    -
    -0.64
    ,
    -0.62
    <bos>
    -0.60
    1
    -0.57
     to
    -0.57
    .
    -0.55
    st
    -0.53
     st
    -0.53
    POSITIVE LOGITS
    PhysRev
    1.09
     vectorielles
    1.08
    aktery
    1.07
     ainfi
    1.00
     vectorielle
    1.00
    bibinfo
    1.00
    BibitemShut
    0.98
     évêque
    0.96
     مُعرِّف
    0.96
     myſelf
    0.96
    Activations Density 1.609%

    No Known Activations