© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 1673
    Prev
    Next
    INDEX
    Explanations

    words, code snippets, and phrases that show up in different programming contexts and documentation.

    oai_token-act-pair · gemini-2.0-flash

    code / websites

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    +#+#
    -0.94
    UnusedPrivate
    -0.85
    BeginInit
    -0.85
    DockStyle
    -0.82
     AssemblyCompany
    -0.81
     propOrder
    -0.78
    IUrlHelper
    -0.78
     endregion
    -0.78
    OGND
    -0.77
    ImageContext
    -0.75
    POSITIVE LOGITS
    centiles
    0.52
     MCQ
    0.52
    ERG
    0.51
    phu
    0.47
     exc
    0.47
    ){}
    0.46
    SHIRE
    0.46
     gre
    0.46
    grin
    0.46
    endt
    0.46
    Activations Density 25.588%

    No Known Activations