Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 22-GEMMASCOPE-TRANSCODER-16K
    4. 14418
    Prev
    Next
    INDEX
    Explanations

    language related to Japanese language, religion, and culture

    oai_token-act-pair · gemini-2.0-flash

    locations

    np_max-act-logits · 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
     Occidente
    -0.88
     occidentale
    -0.82
     occident
    -0.76
     européennes
    -0.74
     orientale
    -0.67
     occidental
    -0.66
     étrangères
    -0.65
     argint
    -0.65
     nahilalakip
    -0.65
     européens
    -0.65
    POSITIVE LOGITS
     Irish
    0.49
     Ireland
    0.48
     cu
    0.47
     Vietnam
    0.45
     Wisconsin
    0.45
     Israel
    0.45
     Florida
    0.45
     cot
    0.45
    TestMethod
    0.44
    PMailer
    0.42
    Activations Density 0.979%

    No Known Activations