© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 5819
    Prev
    Next
    INDEX
    Explanations

    code-related words or symbols, particularly in languages like C# or Ruby as indicated by the file extensions

    oai_token-act-pair · gemini-2.0-flash

    coding snippets

    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
    #![
    -0.82
    èdia
    -0.65
    jspx
    -0.65
    SequentialGroup
    -0.63
    queryInterface
    -0.60
     fréqu
    -0.59
    θρω
    -0.59
     OnInit
    -0.59
    pexpr
    -0.58
     control
    -0.58
    POSITIVE LOGITS
     propOrder
    0.53
    ு
    0.47
     Blue
    0.46
     symbol
    0.44
     observed
    0.44
    蚪
    0.44
    gettyimages
    0.43
     Coen
    0.43
     Observe
    0.43
    Filmografie
    0.42
    Activations Density 4.685%

    No Known Activations