© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 7200
    Prev
    Next
    INDEX
    Explanations

    references to recent trends

    oai_token-act-pair · gemini-2.0-flash

    trend

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
     للمعارف
    -0.77
    IUrlHelper
    -0.69
    complexContent
    -0.63
    AntiForgeryToken
    -0.63
     nahilalakip
    -0.60
     ModelExpression
    -0.57
    GIVEREF
    -0.57
     itſelf
    -0.57
    Brainz
    -0.54
    ppuden
    -0.54
    POSITIVE LOGITS
     trend
    1.37
    trend
    1.22
    Trend
    1.22
     Trend
    1.20
     trends
    1.20
     craze
    1.13
     trending
    1.11
     fad
    1.05
     Trends
    1.02
    trends
    0.97
    Activations Density 0.757%

    No Known Activations