© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 4500
    Prev
    Next
    INDEX
    Explanations

    words or phrases within legal documents that refer to evidence and/or the official court record

    oai_token-act-pair · gemini-2.0-flash

    variations of the word "record"

    np_token-act-pair-logits · gpt-4o-mini

    records

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     ProtoMessage
    -0.65
    DataAnnotations
    -0.61
    webElementXpaths
    -0.60
    urlpatterns
    -0.58
    الحياه
    -0.56
    Portail
    -0.56
    URUS
    -0.54
     Reisedaten
    -0.54
    TestTools
    -0.54
     communiquez
    -0.53
    POSITIVE LOGITS
     record
    3.23
    record
    2.80
     Record
    2.53
     RECORD
    2.41
    Record
    2.38
    RECORD
    2.08
     records
    1.95
     récord
    1.82
    records
    1.77
     rekord
    1.71
    Activations Density 2.201%

    No Known Activations