© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 13591
    Prev
    Next
    INDEX
    Explanations

    words that function as labels for data in scientific reports

    oai_token-act-pair · gemini-2.0-flash

    academic papers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    .
    -0.60
    <eos>
    -0.59
    ?
    -0.53
     i
    -0.51
    tu
    -0.50
     I
    -0.50
    ↵
    -0.49
    x
    -0.48
    io
    -0.48
    new
    -0.48
    POSITIVE LOGITS
     propOrder
    1.02
     дописавши
    1.00
    AddTagHelper
    0.98
     Lightboxes
    0.96
     lenker
    0.94
    extAlignment
    0.94
    InitVars
    0.90
    Identyfik
    0.88
    Autoritní
    0.87
     Efq
    0.86
    Activations Density 5.990%

    No Known Activations