© 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. 11439
    Prev
    Next
    INDEX
    Explanations

    mentions of restricted activity due to socio-political unrest

    oai_token-act-pair · gemini-2.0-flash

    News and technical details

    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
    saraba
    -0.65
    واب
    -0.54
    dojo
    -0.53
     miliardi
    -0.51
     Millar
    -0.49
    autogui
    -0.48
    densed
    -0.47
    ométrique
    -0.47
     ladrillo
    -0.46
    msgTypes
    -0.46
    POSITIVE LOGITS
    odb
    0.64
     earlier
    0.63
     StatefulWidget
    0.57
    ApplicationTests
    0.57
    hoeddwyd
    0.56
    userDao
    0.54
    InitVars
    0.54
    WithMany
    0.53
    SourceChecksum
    0.53
     ویکی‌پدیا
    0.52
    Activations Density 1.898%

    No Known Activations