© 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
    2. Gemma-2-2B
    3. 24-GEMMASCOPE-TRANSCODER-16K
    4. 3568
    Prev
    Next
    INDEX
    Explanations

    mathematical or statistical notation or code

    oai_token-act-pair · gemini-2.0-flash

    Code and 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_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
     Doherty
    -0.74
     Dutton
    -0.71
     Sait
    -0.68
    FetchType
    -0.66
     Adviser
    -0.66
     Vergara
    -0.63
     Cleo
    -0.61
     Cough
    -0.61
     Koy
    -0.61
     Gould
    -0.60
    POSITIVE LOGITS
     Lugo
    0.68
     Jamestown
    0.65
     gewor
    0.63
     Valentina
    0.62
    Cyfeiriadau
    0.60
     capitol
    0.60
     stethoscope
    0.60
     Kand
    0.59
     Athen
    0.59
     Hawthorne
    0.59
    Activations Density 5.582%

    No Known Activations