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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 12560
    Prev
    Next
    INDEX
    Explanations

    locations in the text for names, especially when followed by titles or roles and dates

    oai_token-act-pair · gemini-2.0-flash

    reporting, legal documents

    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
    WithIOException
    -0.70
    riwal
    -0.61
     mẽ
    -0.56
    chi
    -0.52
    AsUp
    -0.50
    DeleteBehavior
    -0.49
     TDP
    -0.49
    soort
    -0.49
     windows
    -0.49
     Platform
    -0.48
    POSITIVE LOGITS
    ReusableCell
    0.66
    ContentAsync
    0.64
    RenderAtEndOf
    0.62
     GlobalKey
    0.61
     Salim
    0.54
    invokeLater
    0.52
     Erwä
    0.51
     MotionEvent
    0.51
    ArgumentParser
    0.50
    cabulary
    0.49
    Activations Density 2.727%

    No Known Activations