© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 13756
    Prev
    Next
    INDEX
    Explanations

    the word "country" and related pluralizations or inflections

    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_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
    -2.47
    country
    -2.22
    Country
    -2.13
     Country
    -2.09
     COUNTRY
    -2.00
    COUNTRY
    -1.84
     país
    -1.64
     Paese
    -1.39
     countries
    -1.23
     Countries
    -1.16
    POSITIVE LOGITS
    langer
    0.53
     biens
    0.50
    </thead>
    0.49
    вающая
    0.45
     producciones
    0.44
    stine
    0.43
    kungan
    0.43
     chúng
    0.43
     Guter
    0.43
    oplasmic
    0.42
    Activations Density 0.222%

    No Known Activations