© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 7-GEMMASCOPE-TRANSCODER-16K
    7. 11604
    Prev
    Next
    INDEX
    Explanations

    HTML and Javascript code, especially code related to URLs and templating.

    oai_token-act-pair · gemini-2.0-flash

    code characters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    MemoryWarning
    -0.53
    ВОД
    -0.51
     Conseils
    -0.50
     client
    -0.50
    cad
    -0.48
    δρ
    -0.48
    igin
    -0.47
    StringCopy
    -0.47
    Syna
    -0.47
    schod
    -0.47
    POSITIVE LOGITS
    Personendaten
    0.77
     getItemId
    0.64
    EndGlobalSection
    0.62
     auffi
    0.61
    WaitGroup
    0.60
     myſelf
    0.60
    UnsafeEnabled
    0.60
    EndInit
    0.59
     createSprite
    0.59
    ViewFeatures
    0.59
    Activations Density 1.740%

    No Known Activations