© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 15303
    Prev
    Next
    INDEX
    Explanations

    contractions of "not" or occurrences of "to"

    oai_token-act-pair · gemini-2.0-flash

    Concentration

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     betweenstory
    -0.72
     AssemblyProduct
    -0.66
    migrationBuilder
    -0.63
    addCriterion
    -0.58
     meille
    -0.57
    liesslich
    -0.56
     OFDb
    -0.56
     AssemblyCompany
    -0.56
    TintMode
    -0.55
     pinulongan
    -0.55
    POSITIVE LOGITS
     concentrate
    0.49
     setOpen
    0.48
    concentr
    0.48
    gico
    0.47
     concentration
    0.47
     concentra
    0.46
    Concentration
    0.46
     förstå
    0.46
    setFocus
    0.45
    StandardCharsets
    0.45
    Activations Density 0.244%

    No Known Activations