© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 3933
    Prev
    Next
    INDEX
    Explanations

    sentences describing playing and games

    oai_token-act-pair · gemini-2.0-flash

    game-related nouns and terms

    np_token-act-pair-logits · gpt-4o-mini

    play

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     kaarangay
    -0.73
     &___
    -0.67
    JspWriter
    -0.66
    +#+#
    -0.65
    ंदीखरीदारी
    -0.65
     protoimpl
    -0.64
     ویکی‌پدی
    -0.59
     volando
    -0.58
    */;
    -0.57
     سكانية
    -0.57
    POSITIVE LOGITS
    TacToe
    0.57
     tag
    0.56
    autoconfigure
    0.55
     Super
    0.52
    CIOS
    0.51
    NOPQRST
    0.50
    комиться
    0.49
    EnableWeb
    0.49
     cat
    0.48
    ContextHolder
    0.47
    Activations Density 3.274%

    No Known Activations