© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 8-GEMMASCOPE-TRANSCODER-16K
    7. 3138
    Prev
    Next
    INDEX
    Explanations

    figure references and reference numerals

    oai_token-act-pair · gemini-2.0-flash

    numeral reference

    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
    IsContent
    -0.55
     Mayr
    -0.55
     Ghosh
    -0.54
    逅
    -0.52
    url
    -0.52
     Jost
    -0.50
     Myrtle
    -0.48
     garlic
    -0.48
    ('@
    -0.47
     risk
    -0.47
    POSITIVE LOGITS
     CreateTagHelper
    0.94
     esternos
    0.65
     оригіналу
    0.60
    CloseOperation
    0.59
    ГЛА
    0.58
    EndContext
    0.58
    illants
    0.57
    WriteTagHelper
    0.56
     Савезне
    0.54
     kaarangay
    0.53
    Activations Density 1.386%

    No Known Activations