© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 10187
    Prev
    Next
    INDEX
    Explanations

    words related to data privacy and security, especially concerning online information.

    oai_token-act-pair · gemini-2.0-flash

    data privacy

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    ViewImports
    -0.70
     ")");
    -0.65
     سكانية
    -0.60
    thâu
    -0.60
     vuitton
    -0.60
    ReusableCell
    -0.59
     linkovi
    -0.57
     محفوظة
    -0.56
     autorytatywna
    -0.56
    Rüyada
    -0.54
    POSITIVE LOGITS
     pinulongan
    0.56
    cellation
    0.49
     Registrar
    0.48
    thschild
    0.48
     zare
    0.47
    
    0.47
     Gifford
    0.46
     vns
    0.46
     Gif
    0.45
     Provision
    0.45
    Activations Density 12.833%

    No Known Activations