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. 0-GEMMASCOPE-TRANSCODER-16K
    4. 7176
    Prev
    Next
    INDEX
    Explanations

    words associated with visual things that people like, such as fashion, craft, decor, and food.

    oai_token-act-pair · gemini-2.0-flash

    design and style

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    ]--;
    -0.81
     greateſt
    -0.79
    tvguidetime
    -0.78
     Efq
    -0.77
    новништво
    -0.76
    yczą
    -0.75
     ſame
    -0.75
     ſmall
    -0.74
     zelve
    -0.74
     beſt
    -0.73
    POSITIVE LOGITS
    <bos>
    0.68
    '
    0.56
     StatelessWidget
    0.50
     StatefulWidget
    0.49
    lgari
    0.48
    ’
    0.47
     initComponents
    0.46
    Art
    0.46
    `
    0.46
    MeasureSpec
    0.45
    Activations Density 1.777%

    No Known Activations