© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-GEMMASCOPE-TRANSCODER-16K
    7. 11334
    Prev
    Next
    INDEX
    Explanations

    the word "delete" or "remove" within code snippets or command descriptions

    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_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    delete
    -1.98
     delete
    -1.97
     Delete
    -1.68
    Delete
    -1.59
     deleting
    -1.52
     deleted
    -1.47
     deletes
    -1.38
    DELETE
    -1.23
     DELETE
    -1.23
     Deletes
    -1.14
    POSITIVE LOGITS
     onCancelled
    0.89
     שוליים
    0.78
    Datuak
    0.78
    ArrowToggle
    0.72
    دانشنامهٔ
    0.71
    AndEndTag
    0.70
     HttpNotFound
    0.68
    posedge
    0.66
    MigrationBuilder
    0.66
    IndentedString
    0.65
    Activations Density 1.642%

    No Known Activations