© 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. 25-GEMMASCOPE-TRANSCODER-16K
    4. 6179
    Prev
    Next
    INDEX
    Explanations

    various bits of markup like HTML, code, timestamps, and acronyms.

    oai_token-act-pair · gemini-2.0-flash

    numerical data reporting

    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
     Eighth
    -0.85
     eight
    -0.84
     eighth
    -0.84
     Eight
    -0.82
    8
    -0.81
     huit
    -0.73
     ocho
    -0.65
    Eight
    -0.63
     eighties
    -0.63
     oito
    -0.61
    POSITIVE LOGITS
     ExecuteAsync
    0.88
    rungsseite
    0.62
     σή
    0.57
    IsContent
    0.56
    fromnode
    0.55
    CommandHandler
    0.55
     تضيفلها
    0.52
     Busse
    0.52
    chehen
    0.52
     dłu
    0.52
    Activations Density 3.464%

    No Known Activations