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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 12983
    Prev
    Next
    INDEX
    Explanations

    mentions of embassies and consulates, especially in relation to countries

    oai_token-act-pair · gemini-2.0-flash

    words related to embassy and diplomatic missions

    np_token-act-pair-logits · gpt-4o-mini

    diplomatic missions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    expandindo
    -0.75
     EconPapers
    -0.75
    izr
    -0.71
    istoitu
    -0.71
    RectangleBorder
    -0.71
    Datuak
    -0.69
     ویکی‌پدیای
    -0.68
     Roskov
    -0.67
     ISNI
    -0.66
    elemField
    -0.66
    POSITIVE LOGITS
     mission
    0.90
     Mission
    0.79
    Mission
    0.75
     missions
    0.67
    mission
    0.67
     MISSION
    0.64
    miss
    0.61
    MISSION
    0.60
     Missions
    0.60
     miss
    0.60
    Activations Density 0.574%

    No Known Activations