© 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. 1681
    Prev
    Next
    INDEX
    Explanations

    technical documentation related to physical objects or processes

    oai_token-act-pair · gemini-2.0-flash

    Hardware/mechanical parts

    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
    发表于
    -0.45
     Heller
    -0.44
     FetchType
    -0.44
    êche
    -0.44
    quiel
    -0.44
    ensaft
    -0.44
     chaus
    -0.43
    îtres
    -0.43
    ñana
    -0.43
     DSP
    -0.43
    POSITIVE LOGITS
     kaarangay
    0.75
    Personensuche
    0.73
     AssemblyCulture
    0.73
    sizeCache
    0.66
    XtraReports
    0.65
    RTEE
    0.65
     EconPapers
    0.65
    InitVars
    0.65
    
    0.62
     NSCoder
    0.61
    Activations Density 1.091%

    No Known Activations