© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 11859
    Prev
    Next
    INDEX
    Explanations

    the demonym "American" when used to describe ethnicity or origin

    oai_token-act-pair · gemini-2.0-flash

    Americans

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     Monfieur
    -0.75
     enfans
    -0.74
     Shakspeare
    -0.72
    principalColumn
    -0.71
     ſmall
    -0.71
     Jefus
    -0.70
     Chriſt
    -0.69
     shewn
    -0.65
     Cæsar
    -0.65
     ſeveral
    -0.64
    POSITIVE LOGITS
     Administrativna
    0.83
    +#+#
    0.79
    sidemargin
    0.73
     lenker
    0.70
     يتيمه
    0.67
    发表于
    0.63
    sizeCache
    0.61
    Хьажоргаш
    0.58
    iastes
    0.57
     NSCoder
    0.57
    Activations Density 0.592%

    No Known Activations