Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 8-GEMMASCOPE-TRANSCODER-16K
    4. 732
    Prev
    Next
    INDEX
    Explanations

    scientific and technical writing (mathematics, programming, engineering)

    oai_token-act-pair · gemini-2.0-flash

    academic writing

    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
    featureID
    -0.50
     TestBed
    -0.48
    dem
    -0.47
    apunov
    -0.46
    ''
    -0.44
     method
    -0.44
     UIKit
    -0.44
    šev
    -0.44
     viviendo
    -0.44
    FileNotFound
    -0.43
    POSITIVE LOGITS
     dAtA
    0.76
    contentLoaded
    0.67
    MemoryWarning
    0.65
    "])
    
    0.61
    )");
    
    0.60
    ")));
    
    0.59
    "):
    
    0.58
    )";
    
    0.58
    '},
    
    0.58
     ligiloj
    0.57
    Activations Density 2.129%

    No Known Activations