© 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. 3939
    Prev
    Next
    INDEX
    Explanations

    Japanese text, especially related to programming and error messages

    oai_token-act-pair · gemini-2.0-flash

    technical and foreign texts

    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
    ')")
    -0.84
    )");
    
    -0.83
    "]];
    -0.81
    ."));
    -0.80
    ")){
    
    -0.79
    $")
    -0.79
    "])
    
    -0.77
    "])){
    -0.77
    "]));
    -0.77
    =$?
    -0.76
    POSITIVE LOGITS
    DockStyle
    0.48
     pleaſure
    0.47
     quæ
    0.47
     paſſ
    0.47
     Jurí
    0.47
     keç
    0.46
    WebVitals
    0.45
    ISupport
    0.45
    richTextPanel
    0.44
     ejus
    0.44
    Activations Density 0.650%

    No Known Activations