© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 7231
    Prev
    Next
    INDEX
    Explanations

    text in scientific publications, especially descriptions of methodology and objectives.

    oai_token-act-pair · gemini-2.0-flash

    Mass spectrometry

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    AnchorStyles
    -0.60
    Cursors
    -0.57
     Abp
    -0.53
     Knochen
    -0.52
    alsy
    -0.52
    rodalom
    -0.51
     preservatives
    -0.51
     borra
    -0.51
    usaha
    -0.50
     peacock
    -0.50
    POSITIVE LOGITS
    PreferredItem
    0.57
    Хьажоргаш
    0.56
    oa̍t
    0.51
     onPostExecute
    0.50
     Accesat
    0.50
    :✨
    0.50
    principalTable
    0.50
     Hye
    0.47
    sendRedirect
    0.47
     سياس
    0.45
    Activations Density 1.392%

    No Known Activations