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. 688
    Prev
    Next
    INDEX
    Explanations

    sentences about the creative process of making movies and tv shows

    oai_token-act-pair · gemini-2.0-flash

    script writing

    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
    Hozzáférés
    -0.47
    ftime
    -0.45
     casera
    -0.43
    helf
    -0.41
     Daarom
    -0.41
     ๆ
    -0.38
    lectric
    -0.37
     ویکی‌پدیای
    -0.37
     везе
    -0.36
    mazan
    -0.36
    POSITIVE LOGITS
    ViewImports
    0.76
    SourceChecksum
    0.72
    __':
    0.71
     CreateTagHelper
    0.68
    TypedDataSet
    0.67
     pinulongan
    0.67
    expandindo
    0.66
    TestingModule
    0.65
    encodeWith
    0.65
    __':
    
    0.64
    Activations Density 2.787%

    No Known Activations