© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 2908
    Prev
    Next
    INDEX
    Explanations

    words referring to nations or national media

    oai_token-act-pair · gemini-2.0-flash

    global

    np_max-act-logits · gemini-2.0-flash

    countries

    np_max-act-logits · gpt-5-mini
    Triggered by @chenshw0109
    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
    Negative Logits
     country
    -1.92
     nation
    -1.81
    country
    -1.59
    Country
    -1.56
     Country
    -1.56
     national
    -1.49
     Nation
    -1.48
     país
    -1.46
     COUNTRY
    -1.44
    nation
    -1.43
    POSITIVE LOGITS
     global
    0.80
     Efq
    0.74
    Global
    0.72
     متعلقه
    0.72
    global
    0.71
     GLOBAL
    0.69
     mundial
    0.67
     worlds
    0.66
     Global
    0.65
     globally
    0.65
    Activations Density 2.913%

    No Known Activations