© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 4-GEMMASCOPE-TRANSCODER-16K
    4. 13045
    Prev
    Next
    INDEX
    Explanations

    the word "title" and words associated with titles, potentially of books, movies, or sports teams

    oai_token-act-pair · gemini-2.0-flash

    title

    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
     title
    -2.50
     titles
    -2.16
     Title
    -2.08
    Title
    -1.95
    title
    -1.91
     Titles
    -1.84
     TITLE
    -1.80
     título
    -1.72
     titel
    -1.71
     Titel
    -1.70
    POSITIVE LOGITS
    SequentialGroup
    0.78
    Kanpo
    0.64
     AdapterView
    0.60
     DriverManager
    0.59
    extAlignment
    0.55
    webElement
    0.55
     الرياضيه
    0.55
    躇
    0.54
    UITableViewCell
    0.54
     MyApp
    0.54
    Activations Density 5.212%

    No Known Activations