© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 12835
    Prev
    Next
    INDEX
    Explanations

    code snippets related to UI element selection and manipulation

    oai_token-act-pair · gemini-2.0-flash

    code punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    Kaieteur
    -0.54
    IBRATION
    -0.50
     Condition
    -0.50
     little
    -0.49
     tune
    -0.47
     reyes
    -0.47
    romy
    -0.47
    Kenmerken
    -0.47
    anee
    -0.47
     changes
    -0.47
    POSITIVE LOGITS
    EndGlobalSection
    0.80
    RenderAtEndOf
    0.80
     Réponses
    0.77
    contentLoaded
    0.73
    IndentedString
    0.71
    EndInit
    0.71
     CreateTagHelper
    0.71
    QMetaType
    0.68
    setVerticalGroup
    0.65
     ویکی‌پدی
    0.64
    Activations Density 0.324%

    No Known Activations