© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 5626
    Prev
    Next
    INDEX
    Explanations

    names of places located in Europe

    oai_token-act-pair · gemini-2.0-flash

    city names

    np_max-act · gemini-2.0-flash

    European capitals

    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_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
     Krakow
    -1.66
     Bucharest
    -1.64
     Ljubljana
    -1.63
     Latvian
    -1.61
     Athenian
    -1.59
     Sicilian
    -1.59
     Florentine
    -1.59
     Slovenian
    -1.59
     Quito
    -1.58
     Kraków
    -1.58
    POSITIVE LOGITS
     Central
    0.91
     West
    0.81
     Ber
    0.77
     west
    0.77
     east
    0.74
     East
    0.73
     central
    0.73
     Bor
    0.73
     eastern
    0.71
     Greater
    0.71
    Activations Density 4.310%

    No Known Activations