© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 8-GEMMASCOPE-TRANSCODER-16K
    7. 3668
    Prev
    Next
    INDEX
    Explanations

    terms related to scientific experimental design over time and space

    oai_token-act-pair · gemini-2.0-flash

    temporal, time

    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
     nakalista
    -0.71
    AddTagHelper
    -0.64
    Geplaatst
    -0.62
    GeneratedCode
    -0.60
    ListItemIcon
    -0.57
     Rhymes
    -0.57
    Diwedd
    -0.55
     OMITBAD
    -0.55
    XMLSchema
    -0.54
    icali
    -0.54
    POSITIVE LOGITS
    
    0.78
    rungsseite
    0.73
     تضيفلها
    0.59
     percor
    0.51
    pannt
    0.51
     plot
    0.48
    ופן
    0.45
     spanning
    0.44
    شنگ
    0.44
    verlust
    0.44
    Activations Density 3.734%

    No Known Activations