© 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. 9263
    Prev
    Next
    INDEX
    Explanations

    code snippets, especially those related to javascript, error handling, and React Native components

    oai_token-act-pair · gemini-2.0-flash

    Punctuation

    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
     mosques
    -0.59
     gulls
    -0.58
     mosque
    -0.56
    mise
    -0.56
    PreferredItem
    -0.55
     Own
    -0.54
     Mosque
    -0.53
     own
    -0.52
    +:+
    -0.50
    stateProvider
    -0.50
    POSITIVE LOGITS
    <bos>
    0.83
    '))
    0.56
    VERTIS
    0.54
    })]
    0.53
    AccessorTable
    0.53
    setupUi
    0.52
     outwardly
    0.52
     autorytatywna
    0.52
    "}>
    0.52
    ))))))))
    0.51
    Activations Density 4.195%

    No Known Activations