© 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. 7085
    Prev
    Next
    INDEX
    Explanations

    titles and names of people with the word "earned" or "obtained" nearby, suggesting it's looking for summaries of people's education and experience

    oai_token-act-pair · gemini-2.0-flash

    Academic titles

    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
    DockStyle
    -0.48
     reloadData
    -0.43
    ennen
    -0.43
    ועל
    -0.40
    ioneta
    -0.40
    beli
    -0.40
     Hygge
    -0.39
    lappe
    -0.39
    Geplaatst
    -0.39
    Filmographie
    -0.39
    POSITIVE LOGITS
     Ph
    1.65
     MD
    1.41
    Ph
    1.38
     M
    1.30
     MA
    1.23
     PhD
    1.20
    MD
    1.19
     ph
    1.16
     MS
    1.16
     Masters
    1.09
    Activations Density 3.054%

    No Known Activations