© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 11365
    Prev
    Next
    INDEX
    Explanations

    words expressing subjective difficulty or negativity as well as phrases describing a personal project related to OpenGL graphics.

    oai_token-act-pair · gemini-2.0-flash

    software and difficult tasks

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    ToBounds
    -0.56
    itals
    -0.50
    ])));
    -0.49
     كومونز
    -0.49
    رشف
    -0.48
    HomeAsUpEnabled
    -0.48
    ChildScrollView
    -0.47
     Tư
    -0.47
     Wirt
    -0.46
     света
    -0.45
    POSITIVE LOGITS
    RegressionTest
    0.68
    StoryboardSegue
    0.66
    modelBuilder
    0.61
    Билгалдахарш
    0.60
    rungsseite
    0.55
    はじめに
    0.54
    invokeLater
    0.52
    WebServlet
    0.52
     XCTest
    0.49
    UnusedPrivate
    0.49
    Activations Density 2.128%

    No Known Activations