© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 10462
    Prev
    Next
    INDEX
    Explanations

    calls to action, or words related to asking someone to do something.

    oai_token-act-pair · gemini-2.0-flash

    Requests/encouragements

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     ***!
    -0.55
     naturels
    -0.50
    出版年
    -0.48
     noires
    -0.47
     perfectos
    -0.46
     perfecta
    -0.46
     évi
    -0.46
     organisational
    -0.45
     geográfica
    -0.45
    Explanation
    -0.44
    POSITIVE LOGITS
    SharedDtor
    0.91
    EndInit
    0.69
     оригіналу
    0.68
     Pingback
    0.62
     vote
    0.60
     klick
    0.60
    AutoScale
    0.59
    SequentialGroup
    0.59
     tweet
    0.59
     bookmark
    0.59
    Activations Density 1.086%

    No Known Activations