© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 7882
    Prev
    Next
    INDEX
    Explanations

    the word "con" followed by another word

    oai_token-act-pair · gemini-2.0-flash

    con

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     Con
    -2.50
    Con
    -2.48
    con
    -2.48
     con
    -2.30
    CON
    -2.06
     CON
    -1.97
     cons
    -1.29
    コン
    -1.25
    cons
    -1.24
    Kon
    -1.21
    POSITIVE LOGITS
    parsedMessage
    0.90
    ViewFeatures
    0.68
    UserScript
    0.60
    elemField
    0.60
    rrggbb
    0.59
    numerusform
    0.55
     AppCompatTheme
    0.54
    ecap
    0.54
    SBATCH
    0.53
    ocellular
    0.53
    Activations Density 1.881%

    No Known Activations