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. 842
    Prev
    Next
    INDEX
    Explanations

    mathematical equations and transformations, especially those related to image manipulation and conformal mapping

    oai_token-act-pair · gemini-2.0-flash

    mapping

    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
    Battery
    -0.44
     jadx
    -0.42
    rician
    -0.42
     Battery
    -0.42
     battery
    -0.41
     joaat
    -0.40
    ベーション
    -0.40
    battery
    -0.40
    urably
    -0.40
     auri
    -0.39
    POSITIVE LOGITS
    URLException
    0.73
    SPJ
    0.69
    IntoConstraints
    0.65
    rensa
    0.64
     estimés
    0.61
    liefert
    0.58
    تقاوى
    0.58
    CHOR
    0.57
     ExecuteAsync
    0.56
    :✨
    0.56
    Activations Density 2.308%

    No Known Activations