© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 18-GEMMASCOPE-TRANSCODER-16K
    7. 4010
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to VPN-services

    oai_token-act-pair · gemini-2.0-flash

    VPN and offshore accounts

    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
    Negative Logits
    expandindo
    -0.70
    tvguidetime
    -0.62
    NewUrlParser
    -0.62
     cools
    -0.60
    IndentedString
    -0.59
    dubbo
    -0.55
     Foire
    -0.54
    евра
    -0.54
     remplacement
    -0.53
    richTextPanel
    -0.53
    POSITIVE LOGITS
     tax
    0.62
     ligiloj
    0.60
    \{\\
    0.56
     وتسجيلات
    0.55
     Tax
    0.50
    erver
    0.50
    tabular
    0.50
     ujednoznacz
    0.50
    KommentareTeilen
    0.49
    HandlerContext
    0.48
    Activations Density 1.651%

    No Known Activations