© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 6-GEMMASCOPE-TRANSCODER-16K
    7. 14208
    Prev
    Next
    INDEX
    Explanations

    phrases containing "as", "was", "is", "it", "has", "extent", and other "filler" words, that are often found in legal documents.

    oai_token-act-pair · gemini-2.0-flash

    legal documents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    :✨
    -0.77
     Normdatei
    -0.77
    verwijspagina
    -0.74
    rungsseite
    -0.69
     kasarigan
    -0.68
     Saltar
    -0.66
     nakalista
    -0.63
    AccessorTable
    -0.63
    SharedCtor
    -0.63
    นาน
    -0.60
    POSITIVE LOGITS
     AssemblyTitle
    0.75
    ربعة
    0.60
    hard
    0.52
     Fair
    0.49
     kadar
    0.48
     кв
    0.47
     Hard
    0.46
     joaat
    0.45
     plafon
    0.45
     hard
    0.44
    Activations Density 1.989%

    No Known Activations