© 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. 9311
    Prev
    Next
    INDEX
    Explanations

    the word "delete" that appears in code

    oai_token-act-pair · gemini-2.0-flash

    delete

    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
    delete
    -1.54
     delete
    -1.49
     Delete
    -1.26
    Delete
    -1.24
     deletes
    -1.13
    DELETE
    -1.09
     DELETE
    -1.05
     deleted
    -1.05
     deleting
    -1.03
    Deleting
    -0.85
    POSITIVE LOGITS
     Cientí
    0.56
    quelize
    0.56
    istoitu
    0.55
    клопе
    0.54
    \}\\
    0.54
     Bask
    0.54
     للمعارف
    0.54
    초
    0.52
    AndEndTag
    0.52
    vacy
    0.52
    Activations Density 0.428%

    No Known Activations