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. 20-GEMMASCOPE-TRANSCODER-16K
    4. 14289
    Prev
    Next
    INDEX
    Explanations

    text discussing FDA approval, medical treatments with brand names, medical studies and corporations with medical products

    oai_token-act-pair · gemini-2.0-flash

    Code 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_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    hotos
    -0.45
     comarca
    -0.44
    ophyll
    -0.43
     organizer
    -0.41
     organizing
    -0.40
    expandindo
    -0.40
    recrow
    -0.40
    @
    -0.39
     max
    -0.39
    aternary
    -0.38
    POSITIVE LOGITS
    __':
    
    0.81
    MigrationBuilder
    0.80
    __":
    
    0.79
    `;
    
    0.66
    __":
    0.64
    BindView
    0.64
    }';
    0.64
    ContentAsync
    0.62
     BrowserModule
    0.62
     PhpStorm
    0.61
    Activations Density 0.908%

    No Known Activations