© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 8067
    Prev
    Next
    INDEX
    Explanations

    references to Europe

    oai_token-act-pair · gemini-2.0-flash

    European

    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
     “
    -0.96
     
    -0.77
     a
    -0.71
     more
    -0.71
     much
    -0.70
     so
    -0.67
     the
    -0.67
    ing
    -0.66
    s
    -0.65
     It
    -0.63
    POSITIVE LOGITS
     engraçadas
    1.15
     vectorielles
    1.09
     poichè
    1.06
     femininas
    1.03
     vectorielle
    1.03
     illustrazione
    1.03
     amitié
    1.02
     artesanales
    1.02
     urbanas
    1.02
     turístico
    1.01
    Activations Density 1.823%

    No Known Activations