© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 13169
    Prev
    Next
    INDEX
    Explanations

    Devanagari characters and Hebrew quotation marks.

    oai_token-act-pair · gemini-2.0-flash

    mathematical equations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     if
    -0.59
     in
    -0.57
     that
    -0.57
    â
    -0.56
     au
    -0.56
     et
    -0.55
     exception
    -0.54
     why
    -0.54
     or
    -0.54
     what
    -0.52
    POSITIVE LOGITS
     transfieras
    0.83
    seamnă
    0.81
     للاسماء
    0.81
     otomatig
    0.78
     propOrder
    0.75
    CloseOperation
    0.74
     Paglinawan
    0.74
     متعلقه
    0.73
    Personensuche
    0.72
     crdi
    0.72
    Activations Density 1.026%

    No Known Activations