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. 16190
    Prev
    Next
    INDEX
    Explanations

    descriptive words used to sell vehicles

    oai_token-act-pair · gemini-2.0-flash

    attention

    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
    UpInside
    -0.52
    gesch
    -0.51
    stdc
    -0.50
    shel
    -0.48
     khung
    -0.45
    jgl
    -0.45
    getMenuInflater
    -0.45
    kiri
    -0.44
     bottom
    -0.43
    premi
    -0.43
    POSITIVE LOGITS
     attention
    1.34
    attention
    1.22
     Attention
    1.21
     ATTENTION
    1.14
    Attention
    1.13
     attracting
    0.95
     eye
    0.95
     attract
    0.92
     Aufmerksamkeit
    0.92
     attentions
    0.90
    Activations Density 0.710%

    No Known Activations