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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 14399
    Prev
    Next
    INDEX
    Explanations

    words related to browser management, ad blocking, programming and website documentation

    oai_token-act-pair · gemini-2.0-flash

    internet browsing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    出版年
    -0.65
    TagMode
    -0.64
    InitVars
    -0.62
    IntoConstraints
    -0.60
    errHandler
    -0.59
    BURGH
    -0.58
    PropertyChanging
    -0.56
     AssemblyCulture
    -0.54
    +#+#
    -0.53
     Huerta
    -0.53
    POSITIVE LOGITS
    UserScript
    0.55
     WebView
    0.54
    Cordialement
    0.52
     ujednoznacz
    0.51
     JSONException
    0.49
     mû
    0.48
     referrerpolicy
    0.48
    RegistryLite
    0.48
     Firefox
    0.47
     Chromium
    0.46
    Activations Density 1.707%

    No Known Activations