© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 14205
    Prev
    Next
    INDEX
    Explanations

    adjectives and nouns related to countries or international relations as well as indefinite articles.

    oai_token-act-pair · gemini-2.0-flash

    countries and nations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     states
    -0.72
    Govern
    -0.67
     States
    -0.62
     STATES
    -0.62
    StoryboardSegue
    -0.60
    ArrowToggle
    -0.60
     שוליים
    -0.59
     peoples
    -0.58
    States
    -0.58
    Ikus
    -0.57
    POSITIVE LOGITS
     country
    2.23
    country
    1.86
     Country
    1.68
    Country
    1.67
     COUNTRY
    1.66
     nation
    1.52
     país
    1.48
    COUNTRY
    1.45
     negara
    1.16
     страну
    1.16
    Activations Density 5.760%

    No Known Activations