© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 1730
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to hunting.

    oai_token-act-pair · gemini-2.0-flash

    game

    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
     noDo
    -0.57
     ویکی‌پدیا
    -0.57
    alium
    -0.56
     Michoacán
    -0.53
    fastjson
    -0.53
    giarism
    -0.53
     fhew
    -0.53
    Xaml
    -0.53
     dieux
    -0.51
     rois
    -0.50
    POSITIVE LOGITS
     game
    2.58
    game
    2.22
     Game
    2.02
    Game
    2.02
     GAME
    1.91
    GAME
    1.70
    ゲーム
    1.46
     games
    1.38
    游戏
    1.36
     jogo
    1.34
    Activations Density 5.591%

    No Known Activations