© 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. 15485
    Prev
    Next
    INDEX
    Explanations

    sentences in which words like "a", "is", "or", "with", "metal" are present

    oai_token-act-pair · gemini-2.0-flash

    random technical descriptions

    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
     layui
    -0.60
     leksikon
    -0.59
    
    -0.57
    tagHelper
    -0.53
    Espèce
    -0.53
    بوابة
    -0.49
     /\.
    -0.49
    fileID
    -0.48
    mybatisplus
    -0.48
    farm
    -0.47
    POSITIVE LOGITS
    IntoConstraints
    0.62
    ритори
    0.59
    ställning
    0.55
    RectangleBorder
    0.54
    спита
    0.53
    úsica
    0.51
    })));
    0.51
     lenker
    0.50
    IonicModule
    0.50
    expects
    0.50
    Activations Density 1.586%

    No Known Activations