© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 16310
    Prev
    Next
    INDEX
    Explanations

    French and Arabic words related to quizzes

    oai_token-act-pair · gemini-2.0-flash

    Non-English text

    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
    ̍t
    -0.74
     loren
    -0.63
     cellar
    -0.60
    usstsein
    -0.59
    ]();
    -0.59
     projectors
    -0.58
     gundam
    -0.57
     Lodi
    -0.57
    cknow
    -0.56
    Переваги
    -0.56
    POSITIVE LOGITS
    <bos>
    1.87
    ,
    0.71
     the
    0.69
     it
    0.68
    ⓧ
    0.67
    bootstrapcdn
    0.66
    ActionCreators
    0.65
     ب
    0.61
     त
    0.60
    #!/
    0.60
    Activations Density 0.591%

    No Known Activations