© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 11106
    Prev
    Next
    INDEX
    Explanations

    variable names in various coding languages that deal with memory or string manipulation

    oai_token-act-pair · gemini-2.0-flash

    Code

    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
    anguages
    -0.56
     besar
    -0.54
    RegressionTest
    -0.54
     ilman
    -0.54
     ویکی‌پدیای
    -0.53
     proposons
    -0.52
    timewa
    -0.51
    ReusableCell
    -0.50
    GEBURTS
    -0.50
    :✨
    -0.50
    POSITIVE LOGITS
    WebVitals
    0.68
    BeginContext
    0.65
    OGND
    0.62
    resave
    0.58
    󠁣
    0.55
    //
    0.55
     GenerationType
    0.54
    Хьажоргаш
    0.52
    pageY
    0.50
     IBOutlet
    0.50
    Activations Density 1.125%

    No Known Activations