© 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. 4545
    Prev
    Next
    INDEX
    Explanations

    lines of code that import libraries in React Native

    oai_token-act-pair · gemini-2.0-flash

    from

    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
     from
    -0.75
    <bos>
    -0.63
    ↵
    -0.46
    from
    -0.43
      
    -0.43
    CompleteListener
    -0.42
     the
    -0.42
    n
    -0.42
    1
    -0.42
    ↵↵
    -0.41
    POSITIVE LOGITS
    adaptiveStyles
    0.96
    complexContent
    0.86
    complexType
    0.76
    :✨
    0.76
     ujednoznacz
    0.75
     للمعارف
    0.74
    +#+#
    0.73
    KommentareTeilen
    0.72
     crdi
    0.72
     BoxFit
    0.71
    Activations Density 0.402%

    No Known Activations