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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 8088
    Prev
    Next
    INDEX
    Explanations

    code snippets related to web development, looking for variables, HTML tags, and PHP

    oai_token-act-pair · gemini-2.0-flash

    ending in "Id"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     Illumination
    -0.53
     oscillations
    -0.51
    Fractal
    -0.50
    Inertia
    -0.50
     oscillating
    -0.49
     Instability
    -0.48
    Contours
    -0.48
     thickening
    -0.46
    chunky
    -0.46
     Acceleration
    -0.46
    POSITIVE LOGITS
    UserId
    0.70
    CustomerId
    0.62
    OrderId
    0.62
    ProductId
    0.60
    UserID
    0.59
    userID
    0.59
    CategoryId
    0.59
    EmployeeId
    0.59
    ProductID
    0.59
    CompanyId
    0.57
    Activations Density 21.854%

    No Known Activations