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. 7-GEMMASCOPE-TRANSCODER-16K
    4. 6784
    Prev
    Next
    INDEX
    Explanations

    words and phrases describing features of a Peugeot 3008 SUV

    oai_token-act-pair · gemini-2.0-flash

    lighting

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    BagLayout
    -0.57
    TURE
    -0.51
    isRequired
    -0.50
    DataPropertyName
    -0.48
     civil
    -0.48
     yeast
    -0.47
     TextAppearance
    -0.47
    CompilerServices
    -0.47
    StoryboardSegue
    -0.45
    ValueStyle
    -0.45
    POSITIVE LOGITS
    <bos>
    0.66
     bağlantılar
    0.63
     disambiguazione
    0.60
    IntoConstraints
    0.60
     insuffisamment
    0.59
     indisponible
    0.58
    getKeyCode
    0.56
    bleshooting
    0.56
     Femmes
    0.55
     spécialisée
    0.55
    Activations Density 1.124%

    No Known Activations