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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 14446
    Prev
    Next
    INDEX
    Explanations

    multiple, possibly related, things: likely a combination of research paper citations, earthquake-related language, sequences of parentheses with conjunctions, and code documentation.

    oai_token-act-pair · gemini-2.0-flash

    Turkish words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    RectangleBorder
    -1.12
    ंदीखरीदारी
    -0.99
    BeginContext
    -0.98
    ✨:
    -0.96
     ComVisible
    -0.94
     BoxDecoration
    -0.93
     AssemblyTitle
    -0.92
     EconPapers
    -0.92
     للمعارف
    -0.92
    ValueStyle
    -0.90
    POSITIVE LOGITS
     vektör
    0.57
     oyuncak
    0.54
    юще
    0.53
     bilim
    0.52
     tavsiye
    0.52
     tartış
    0.52
     bilgisayar
    0.50
     şek
    0.49
     keş
    0.49
     yarat
    0.49
    Activations Density 0.278%

    No Known Activations