© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 12380
    Prev
    Next
    INDEX
    Explanations

    technical, scientific, or academic language

    oai_token-act-pair · gemini-2.0-flash

    scientific/technical texts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     scolaires
    -0.55
     mør
    -0.48
     considérons
    -0.45
    が含ま
    -0.45
     gezin
    -0.44
     nuage
    -0.44
     defaultstate
    -0.43
    inium
    -0.43
    onAttach
    -0.43
    harapkan
    -0.43
    POSITIVE LOGITS
    archiviato
    0.69
    SharedDtor
    0.64
    mybatisplus
    0.62
    afficheront
    0.61
    ChildIndex
    0.60
    HandlerContext
    0.60
     noDo
    0.59
     NSCoder
    0.58
    ьаж
    0.57
    TagHelper
    0.57
    Activations Density 36.547%

    No Known Activations