© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 15072
    Prev
    Next
    INDEX
    Explanations

    code-related keywords, especially those related to object creation, UI styling, or XML parsing.

    oai_token-act-pair · gemini-2.0-flash

    create

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
     Create
    -0.96
    Create
    -0.92
    create
    -0.91
     CREATE
    -0.79
    CREATE
    -0.79
     create
    -0.77
    Creating
    -0.76
     creating
    -0.74
     Creates
    -0.73
     Creating
    -0.73
    POSITIVE LOGITS
    NameInMap
    0.67
     estekak
    0.67
     nakalista
    0.64
     intptr
    0.63
    aronder
    0.60
    rawDesc
    0.59
    قایناق‌لار
    0.59
     gyhoeddwyd
    0.58
    UTERS
    0.56
    Bronnen
    0.55
    Activations Density 7.707%

    No Known Activations