© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 12663
    Prev
    Next
    INDEX
    Explanations

    the word "Union" preceded sometimes by "European", along with other geographic designations such as country codes and place names

    oai_token-act-pair · gemini-2.0-flash

    Union

    np_max-act · gemini-2.0-flash

    Union

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
    Personendaten
    -0.85
     تضيفلها
    -0.74
    makeConstraints
    -0.72
    Personensuche
    -0.70
     StringField
    -0.68
    contentLoaded
    -0.68
    ISupport
    -0.68
    evos
    -0.66
    setCellValue
    -0.66
    ̍t
    -0.66
    POSITIVE LOGITS
    غرب
    0.54
     renforcé
    0.54
    getJSON
    0.53
     alumínio
    0.50
    amling
    0.50
     Humanos
    0.49
    yordu
    0.48
    šet
    0.48
    lıyor
    0.48
    lusconi
    0.47
    Activations Density 0.783%

    No Known Activations