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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 8109
    Prev
    Next
    INDEX
    Explanations

    place names in Hong Kong, especially those related to Tsing Yi Island

    oai_token-act-pair · gemini-2.0-flash

    wikipedia

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     HK
    -0.65
     Hong
    -0.63
     تضيفلها
    -0.62
    bootstrapcdn
    -0.61
    Hong
    -0.60
     Malta
    -0.59
    terase
    -0.57
    HK
    -0.56
    UIControlState
    -0.55
    ///</
    -0.54
    POSITIVE LOGITS
     propOrder
    0.56
     کیلومتر
    0.51
     ся
    0.49
     craindre
    0.47
     demais
    0.46
     σο
    0.46
     Esq
    0.45
     Winaray
    0.45
    walde
    0.45
    poons
    0.45
    Activations Density 2.661%

    No Known Activations