© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 1771
    Prev
    Next
    INDEX
    Explanations

    mentions countries (either their names or adjectives of them)

    oai_token-act-pair · gemini-2.0-flash

    country

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     NgModule
    -0.49
    Organisateur
    -0.45
    AddHtmlAttribute
    -0.45
    āv
    -0.44
    Referințe
    -0.44
     Bhd
    -0.44
    例句
    -0.43
    matan
    -0.41
     aparcamiento
    -0.40
    صحاب
    -0.40
    POSITIVE LOGITS
     country
    1.29
    country
    1.09
     nation
    1.00
     Country
    0.98
     COUNTRY
    0.93
    Country
    0.93
     Paese
    0.88
     país
    0.85
     countrymen
    0.85
    COUNTRY
    0.85
    Activations Density 2.187%

    No Known Activations