© 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
    3. Gemma-2-2B
    5. 8-GEMMASCOPE-TRANSCODER-16K
    7. 347
    Prev
    Next
    INDEX
    Explanations

    hexadecimal numbers and associated metadata

    oai_token-act-pair · gemini-2.0-flash

    hexadecimal

    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
     تضيفلها
    -0.85
    WebServlet
    -0.76
     Infórmanos
    -0.68
     فريبيس
    -0.67
    awtextra
    -0.67
     WebDriverWait
    -0.65
    Hentet
    -0.65
    scrapy
    -0.61
    ScopeManager
    -0.61
    BeginContext
    -0.60
    POSITIVE LOGITS
    BeginInit
    0.46
    hadur
    0.45
    ="\
    0.43
    idemiology
    0.42
     rowspan
    0.42
     novidades
    0.42
    frastructure
    0.41
     发表于
    0.41
    ='\
    0.41
    enschappe
    0.41
    Activations Density 32.816%

    No Known Activations