© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 4377
    Prev
    Next
    INDEX
    Explanations

    mathematical notation and theorems

    oai_token-act-pair · gemini-2.0-flash

    have

    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
    Negative Logits
     ویکی‌پدی
    -0.99
    脚注の使い方
    -0.96
    TagMode
    -0.90
     للمعارف
    -0.87
    <bos>
    -0.84
    NameInMap
    -0.81
    utilisons
    -0.72
    RectangleBorder
    -0.70
    ніципа
    -0.68
    
    -0.67
    POSITIVE LOGITS
     Mous
    0.48
    ParameterName
    0.44
    hist
    0.43
     diastolic
    0.43
    nous
    0.42
     dio
    0.42
     sacrifice
    0.41
    eared
    0.41
    inse
    0.41
    йка
    0.40
    Activations Density 7.011%

    No Known Activations