© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 660
    Prev
    Next
    INDEX
    Explanations

    the word "add" and related terms and code

    oai_token-act-pair · gemini-2.0-flash

    add

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     AssemblyProduct
    -0.71
    Portail
    -0.65
    SharedCtor
    -0.63
    toThrow
    -0.62
    */),
    -0.59
    Jeografia
    -0.59
    ">+
    -0.58
    quirrel
    -0.57
    copes
    -0.56
    rungsseite
    -0.56
    POSITIVE LOGITS
     CreateTagHelper
    0.54
    ResumeLayout
    0.40
    睨
    0.40
    irchen
    0.39
     GenerationType
    0.38
    paramref
    0.38
    vantage
    0.38
     domina
    0.37
     المصري
    0.36
    cupertino
    0.36
    Activations Density 0.835%

    No Known Activations