© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 7931
    Prev
    Next
    INDEX
    Explanations

    code snippets, especially variables, functions, and other code-related keywords

    oai_token-act-pair · gemini-2.0-flash

    code and programming

    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
    -
    -0.70
    -/
    -0.62
    -%
    -0.60
    /
    -0.60
     class
    -0.60
    protoc
    -0.57
    -(
    -0.56
    -<
    -0.54
    #
    -0.53
     IBOutlet
    -0.51
    POSITIVE LOGITS
    IsContent
    0.59
    transQ
    0.57
     mẽ
    0.55
    eamento
    0.53
     Languedoc
    0.52
    imerick
    0.52
    Diwedd
    0.51
     oreille
    0.51
    Билгалдахарш
    0.51
    opardy
    0.51
    Activations Density 6.238%

    No Known Activations