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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 19-GEMMASCOPE-TRANSCODER-16K
    7. 6502
    Prev
    Next
    INDEX
    Explanations

    tokens occurring at the start of sentences in a paragraph about sleep apnea

    oai_token-act-pair · gemini-2.0-flash

    Symptoms and feelings

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    üyada
    -0.64
    bewerken
    -0.61
    Rüyada
    -0.58
     Zwer
    -0.56
    :][
    -0.55
    RegressionTest
    -0.55
    Dilution
    -0.55
    ografija
    -0.54
    AddTagHelper
    -0.54
    selective
    -0.53
    POSITIVE LOGITS
     betweenstory
    0.63
     depressed
    0.56
     المعيارى
    0.54
     françaises
    0.50
     GenerationType
    0.48
    鬱
    0.47
    FormState
    0.47
    fog
    0.46
     bloating
    0.46
    WebVitals
    0.46
    Activations Density 1.654%

    No Known Activations