© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 13545
    Prev
    Next
    INDEX
    Explanations

    a mix of proper nouns - Japanese names, place names, and potentially medical terminology

    oai_token-act-pair · gemini-2.0-flash

    Citations/Technical documents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    #+#
    -0.79
    parsedMessage
    -0.73
    transQ
    -0.72
    XmlAccessType
    -0.68
    ыгана
    -0.65
    +:+
    -0.59
     itſelf
    -0.59
    WithIOException
    -0.59
    AccessorTable
    -0.57
    rungsseite
    -0.57
    POSITIVE LOGITS
     ngang
    0.50
     dole
    0.48
     ?>"
    0.48
    EndGlobal
    0.46
    ?>"
    0.46
     freiw
    0.44
    latform
    0.43
    izr
    0.43
     Mice
    0.42
     }}"></
    0.42
    Activations Density 3.846%

    No Known Activations