© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 2589
    Prev
    Next
    INDEX
    Explanations

    names of international organizations and publications

    oai_token-act-pair · gemini-2.0-flash

    international

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    شهاد
    -0.65
     courbe
    -0.61
     nargin
    -0.59
     '\\;'
    -0.57
    nalités
    -0.56
     Wiktionnaire
    -0.54
    InputBorder
    -0.54
    migrationBuilder
    -0.53
    렷
    -0.52
    awtextra
    -0.52
    POSITIVE LOGITS
    RegressionTest
    0.63
     onData
    0.54
    HttpConnection
    0.54
     متحده
    0.52
    athy
    0.49
    oglio
    0.48
    scanf
    0.47
    er
    0.47
     Conven
    0.46
     Break
    0.46
    Activations Density 1.223%

    No Known Activations