© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 4553
    Prev
    Next
    INDEX
    Explanations

    words related to academic papers and studies

    oai_token-act-pair · gemini-2.0-flash

    academic studies

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     ddelweddau
    -0.82
     MessageBoxIcon
    -0.76
    }{*}{}
    -0.75
     Biôgrafia
    -0.75
     مشين
    -0.73
     PopupWindow
    -0.71
    +:+
    -0.70
     InputDecoration
    -0.69
     فريبيس
    -0.68
    Cordialement
    -0.67
    POSITIVE LOGITS
    <bos>
    0.84
    Gemeinden
    0.44
      
    0.42
    เร็
    0.41
    list
    0.41
    <h2>
    0.41
    m
    0.41
    //
    0.40
    a
    0.40
    ni
    0.40
    Activations Density 3.036%

    No Known Activations