© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 4835
    Prev
    Next
    INDEX
    Explanations

    titles of books, articles, or other creative works

    oai_token-act-pair · gemini-2.0-flash

    social, political commentary

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DoubleQuotes
    -0.63
     personali
    -0.61
    FontStyle
    -0.60
     becauſe
    -0.59
     formules
    -0.57
    opardy
    -0.57
     myſelf
    -0.56
     itali
    -0.56
     AssemblyCompany
    -0.56
     generali
    -0.56
    POSITIVE LOGITS
     utafitiHapana
    0.61
    sizeCache
    0.59
     MaterialApp
    0.58
    rawDesc
    0.55
    SharedDtor
    0.53
    zeera
    0.53
    tvguidetime
    0.52
    -------
    0.52
    noopener
    0.50
    complexContent
    0.50
    Activations Density 2.696%

    No Known Activations