© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 6750
    Prev
    Next
    INDEX
    Explanations

    the word "script" along with related coding terms

    oai_token-act-pair · gemini-2.0-flash

    script

    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
    Not in Any Lists

    No Comments

    Negative Logits
     script
    -2.75
    Script
    -2.45
     Script
    -2.44
    script
    -2.44
     scripts
    -2.41
     Scripts
    -2.06
     SCRIPT
    -1.91
    SCRIPT
    -1.90
    scripts
    -1.89
    Scripts
    -1.87
    POSITIVE LOGITS
    ConstraintMaker
    0.67
     myſelf
    0.66
     démocr
    0.66
    SharedCtor
    0.63
     siè
    0.60
     aveug
    0.60
    chyma
    0.60
    NgModule
    0.57
    trui
    0.57
     africains
    0.56
    Activations Density 0.472%

    No Known Activations