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. 14917
    Prev
    Next
    INDEX
    Explanations

    mentions of writing, editing and story development

    oai_token-act-pair · gemini-2.0-flash

    Writing

    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
    typeorm
    -0.65
    ngdoc
    -0.65
     للمعارف
    -0.63
     stanovnika
    -0.62
    addGap
    -0.59
    addContainerGap
    -0.58
    новниш
    -0.57
     betweenstory
    -0.57
     Sev
    -0.56
     Butterfield
    -0.56
    POSITIVE LOGITS
    WithIOException
    0.60
     kasarigan
    0.51
     سكانية
    0.47
     tartalomajánló
    0.46
    atiche
    0.44
     للاسماء
    0.44
     amelyek
    0.44
     ThemeData
    0.43
     fiction
    0.42
    SequentialGroup
    0.42
    Activations Density 1.970%

    No Known Activations