© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 8664
    Prev
    Next
    INDEX
    Explanations

    a combination of numbers, symbols, and equations.

    oai_token-act-pair · gemini-2.0-flash

    say "1"

    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
    1
    -0.73
     Monfieur
    -0.61
     १
    -0.59
     ১
    -0.56
     uſed
    -0.54
    १
    -0.54
     Maho
    -0.54
     hoard
    -0.54
     Thirteenth
    -0.50
    Pautan
    -0.50
    POSITIVE LOGITS
    ंदीखरीदारी
    0.81
     IV
    0.81
     II
    0.76
     III
    0.73
    III
    0.71
     four
    0.71
     الحره
    0.71
     Four
    0.70
     Three
    0.69
    makeConstraints
    0.69
    Activations Density 13.747%

    No Known Activations