© 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. 12021
    Prev
    Next
    INDEX
    Explanations

    references to different countries and ethnicities

    oai_token-act-pair · gemini-2.0-flash

    Nationalities

    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
     Japanese
    -1.80
     Italian
    -1.75
     Mexican
    -1.71
     Canadian
    -1.69
     Chinese
    -1.69
    Japanese
    -1.66
     German
    -1.65
     Brazilian
    -1.63
     French
    -1.63
    Italian
    -1.63
    POSITIVE LOGITS
    SourceChecksum
    0.61
     @"/
    0.58
    клопе
    0.58
     مرئيه
    0.58
     GetEnumerator
    0.57
    IContainer
    0.55
    rungsseite
    0.54
    charCodeAt
    0.51
    tanleria
    0.51
     udaler
    0.50
    Activations Density 2.144%

    No Known Activations