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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 3332
    Prev
    Next
    INDEX
    Explanations

    the neuron finds quoted phrases, parenthetical remarks, hyphenated words, and conjunctions

    oai_token-act-pair · gemini-2.0-flash

    text excerpts

    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
     Gorb
    -0.57
     Sociales
    -0.57
     exécu
    -0.56
     demokra
    -0.55
     Retrospective
    -0.55
     Appliances
    -0.54
     Consultation
    -0.54
     carri
    -0.54
     EventArgs
    -0.53
     Wallpapers
    -0.53
    POSITIVE LOGITS
    migrationBuilder
    0.67
    CPtr
    0.66
    findpost
    0.60
    principalTable
    0.59
    টি
    0.54
     дописавши
    0.52
    ltk
    0.52
     تضيفلها
    0.50
    GEBURTS
    0.50
    RTEX
    0.49
    Activations Density 4.537%

    No Known Activations