© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 9822
    Prev
    Next
    INDEX
    Explanations

    seemingly random words, sometimes in a language other than English

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     للمعارف
    -1.04
     autorytatywna
    -1.00
     lenker
    -0.99
    ^(@)
    -0.91
     iſt
    -0.91
    ingeki
    -0.88
     ―――――
    -0.87
     Eſ
    -0.86
    WithIdentifier
    -0.85
    BibitemShut
    -0.85
    POSITIVE LOGITS
    .
    0.40
     flyg
    0.34
     henkilö
    0.33
     mål
    0.33
    ,
    0.33
     –
    0.32
    <sup>
    0.32
    (
    0.32
    <b>
    0.30
     träd
    0.30
    Activations Density 7.973%

    No Known Activations