© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 14482
    Prev
    Next
    INDEX
    Explanations

    words that are very common in research papers or medical documents.

    oai_token-act-pair · gemini-2.0-flash

    under

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    GraphicsUnit
    -0.88
    Diwedd
    -0.83
    protoimpl
    -0.72
     betweenstory
    -0.69
    setViewportView
    -0.69
    awaiter
    -0.68
     estimés
    -0.68
    saraba
    -0.66
    writeFieldEnd
    -0.66
     createSprite
    -0.66
    POSITIVE LOGITS
     under
    3.97
    under
    3.47
    Under
    3.45
     Under
    3.31
     UNDER
    3.03
    UNDER
    2.80
     bajo
    2.38
     unter
    2.34
     sotto
    2.17
     sous
    2.08
    Activations Density 7.919%

    No Known Activations