© 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. 4408
    Prev
    Next
    INDEX
    Explanations

    the word "those" and words immediately adjacent to it

    oai_token-act-pair · gemini-2.0-flash

    those

    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
     kuni
    -0.53
    ladu
    -0.52
     Schnitt
    -0.52
    rhosis
    -0.52
    oidal
    -0.52
    úly
    -0.52
    grees
    -0.51
    batore
    -0.51
    urate
    -0.50
     Weltkrieg
    -0.50
    POSITIVE LOGITS
    mappedBy
    0.63
    Chham
    0.56
     initComponents
    0.52
    )|^{
    0.47
     AssemblyCompany
    0.46
    Personendaten
    0.45
    ={`/
    0.44
    $.
    0.44
    <bos>
    0.44
    \{\\
    0.43
    Activations Density 0.568%

    No Known Activations