Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 4-GEMMASCOPE-TRANSCODER-16K
    4. 13532
    Prev
    Next
    INDEX
    Explanations

    seemingly random occurrences of whitespace or lack thereof between words and punctuation, and isolated punctuation

    oai_token-act-pair · gemini-2.0-flash

    Text snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    المكان
    -0.44
      
    -0.39
    Widths
    -0.38
     जाते
    -0.38
     ویکی‌پدیای
    -0.36
    յու
    -0.36
    ktur
    -0.35
     fundador
    -0.34
    leyeb
    -0.33
     красиво
    -0.33
    POSITIVE LOGITS
    Personensuche
    0.96
    ########.
    0.93
     disambiguazione
    0.77
    TextWatcher
    0.77
    enterOuterAlt
    0.75
    Biographie
    0.69
    tvguidetime
    0.68
    WebVitals
    0.68
    ItemLayout
    0.67
    المشاركات
    0.66
    Activations Density 1.755%

    No Known Activations