© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 1632
    Prev
    Next
    INDEX
    Explanations

    words related to design and construction

    oai_token-act-pair · gemini-2.0-flash

    Construction design

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
     escuchado
    -0.63
    setVerticalGroup
    -0.62
    djangoproject
    -0.60
    ValueStyle
    -0.58
    matchCondition
    -0.57
     linkovi
    -0.56
     MainAxisSize
    -0.54
    WebServlet
    -0.53
    brainly
    -0.52
    ssize
    -0.52
    POSITIVE LOGITS
     drawings
    0.61
     AutoCAD
    0.60
     drafting
    0.59
    脚注の使い方
    0.56
     pencil
    0.54
     drawing
    0.54
     TestBed
    0.54
    AutoScale
    0.54
    saida
    0.52
     detail
    0.52
    Activations Density 1.194%

    No Known Activations