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. 14429
    Prev
    Next
    INDEX
    Explanations

    product descriptions and specifications and whether they fit the specified requirements

    oai_token-act-pair · gemini-2.0-flash

    Product descriptions

    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
    MigrationBuilder
    -0.99
    WriteTagHelper
    -0.85
    RegistryLite
    -0.81
     AssemblyCulture
    -0.78
    balleur
    -0.69
     الاطلاع
    -0.67
    iNdEx
    -0.65
    AntiForgeryToken
    -0.63
     يتيمه
    -0.62
    RectangleBorder
    -0.62
    POSITIVE LOGITS
     ideal
    0.67
     perfect
    0.63
     characterized
    0.60
     compatible
    0.54
     topped
    0.53
     easy
    0.53
    .');
    0.50
     fes
    0.50
    ideal
    0.49
     characterised
    0.47
    Activations Density 1.151%

    No Known Activations