© 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. 8520
    Prev
    Next
    INDEX
    Explanations

    numbers and numerical references, especially in the context of scientific or mathematical notation, including sequences and scientific literature citations

    oai_token-act-pair · gemini-2.0-flash

    code and math

    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
    -0.96
     Shakspeare
    -0.50
    olahan
    -0.44
     
    -0.43
     Urbano
    -0.43
    0
    -0.43
     useAppContext
    -0.43
    optimizer
    -0.40
    ͘
    -0.40
     espacial
    -0.39
    POSITIVE LOGITS
     Six
    0.77
     AssemblyCulture
    0.76
     SIX
    0.72
     referrerpolicy
    0.71
     Eight
    0.71
     Five
    0.71
    GEBURTSDATUM
    0.70
    Życiorys
    0.70
    TintMode
    0.70
     SEVEN
    0.69
    Activations Density 23.449%

    No Known Activations