© 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
    2. Gemma-2-2B
    3. 22-GEMMASCOPE-TRANSCODER-16K
    4. 10653
    Prev
    Next
    INDEX
    Explanations

    mentions of locations in Hong Kong

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     MyBatis
    -0.66
     CascadeType
    -0.60
     CHINESE
    -0.58
     Signalez
    -0.57
    qtype
    -0.56
     Bact
    -0.56
    AsUp
    -0.55
     againſt
    -0.55
     Chinois
    -0.54
     photolibrary
    -0.54
    POSITIVE LOGITS
     Wing
    0.56
    openConnection
    0.51
    fortune
    0.50
     fortune
    0.49
     dim
    0.47
     WING
    0.47
    Wing
    0.46
     Lo
    0.46
     Wah
    0.46
    AutoScaleMode
    0.45
    Activations Density 1.009%

    No Known Activations