© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 7100
    Prev
    Next
    INDEX
    Explanations

    the word "is" and the string "where it's."

    oai_token-act-pair · gemini-2.0-flash

    at

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    Cordialement
    -0.75
    ulihan
    -0.56
    nościo
    -0.53
    extAlignment
    -0.52
     siinä
    -0.50
     dalam
    -0.49
     CURLOPT
    -0.48
    チール
    -0.48
     /\.
    -0.47
    dalam
    -0.47
    POSITIVE LOGITS
     at
    1.53
    At
    1.12
     At
    1.09
    at
    0.96
     AT
    0.75
     atx
    0.66
     tại
    0.59
    SourceChecksum
    0.57
     Atti
    0.57
    IndentedString
    0.57
    Activations Density 1.199%

    No Known Activations