Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 4-GEMMASCOPE-TRANSCODER-16K
    4. 13515
    Prev
    Next
    INDEX
    Explanations

    locations and countries

    oai_token-act-pair · gemini-2.0-flash

    country

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     country
    -2.33
     Country
    -2.13
    Country
    -2.06
    country
    -2.05
     COUNTRY
    -1.95
    COUNTRY
    -1.77
     país
    -1.36
     страны
    -1.05
     countries
    -1.05
     страну
    -1.02
    POSITIVE LOGITS
    tagHelperRunner
    1.00
    ]='\
    0.98
    GEBURTSDATUM
    0.93
    Bronnen
    0.88
    PerformLayout
    0.84
    principalTable
    0.80
    AccessorTable
    0.75
     oprot
    0.73
     HttpHeaders
    0.71
    RegressionTest
    0.70
    Activations Density 3.509%

    No Known Activations