© 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. 13317
    Prev
    Next
    INDEX
    Explanations

    words related to research, help, and diagnosis.

    oai_token-act-pair · gemini-2.0-flash

    Code-related terms

    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
    }{*}{
    -0.62
    "?>
    -0.58
    Geplaatst
    -0.56
    AndEndTag
    -0.54
    はじめに
    -0.51
    )}_{
    -0.51
    */].
    -0.50
     BIBSYS
    -0.49
     }}">
    -0.47
    tib
    -0.47
    POSITIVE LOGITS
    HtmlAttribute
    0.61
    IBOutlet
    0.61
    makeConstraints
    0.60
    DataSnapshot
    0.54
     endblock
    0.53
     MaterialApp
    0.52
    UnitTesting
    0.52
    StoryboardSegue
    0.52
    printLine
    0.51
    slidesPer
    0.51
    Activations Density 0.773%

    No Known Activations