© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 13989
    Prev
    Next
    INDEX
    Explanations

    a variety of seemingly random words or letters, sometimes medical or legal terms

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    zal
    -0.52
    /
    -0.47
     tkinter
    -0.46
    TagHelpers
    -0.44
    hada
    -0.43
     ->
    -0.43
    PageRoute
    -0.43
    espan
    -0.43
     baz
    -0.42
     jeste
    -0.41
    POSITIVE LOGITS
    <bos>
    2.42
     ainfi
    0.95
    GEBURTSDATUM
    0.91
     дописавши
    0.90
     itſelf
    0.88
    __':
    0.88
     Monfieur
    0.86
    __":
    0.83
     myſelf
    0.82
    .")
    0.81
    Activations Density 1.867%

    No Known Activations