© 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. 445
    Prev
    Next
    INDEX
    Explanations

    mathematical and scientific jargon

    oai_token-act-pair · gemini-2.0-flash

    Math equations

    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
     estimation
    -0.60
    Estimation
    -0.52
    metric
    -0.49
     Estimation
    -0.49
    kháu
    -0.48
    ometers
    -0.47
    TintMode
    -0.46
     estimates
    -0.46
     calibrated
    -0.46
     measured
    -0.45
    POSITIVE LOGITS
    AndEndTag
    0.71
    :✨
    0.71
    venser
    0.62
     OMITBAD
    0.59
     يتيمه
    0.59
     particulières
    0.59
    WindowConstants
    0.55
     Odysseus
    0.54
    Begriffsklä
    0.54
    fromnode
    0.53
    Activations Density 6.859%

    No Known Activations