© 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. 1450
    Prev
    Next
    INDEX
    Explanations

    the prefix "De" at the beginning of words, possibly identifying names

    oai_token-act-pair · gemini-2.0-flash

    De

    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
    DockStyle
    -0.74
     ModelExpression
    -0.60
    ChildScrollView
    -0.60
    JpaRepository
    -0.57
    abestanden
    -0.56
     Мексичка
    -0.53
    "}},
    -0.50
    OrNil
    -0.50
     EconPapers
    -0.50
    MemoryWarning
    -0.49
    POSITIVE LOGITS
     שוליים
    0.54
     Chiara
    0.52
     Lucy
    0.47
     Lourdes
    0.47
    verson
    0.45
    Lucie
    0.44
     Leandro
    0.44
    umer
    0.44
    ven
    0.44
    VEN
    0.44
    Activations Density 4.135%

    No Known Activations