© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 14937
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to resources that are free to download and use

    oai_token-act-pair · gemini-2.0-flash

    texts related to copyright and free resources

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

    Free digital content

    np_max-act-logits · gemini-2.0-flash
    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
    Билгалдахарш
    -0.59
    IMPORTED
    -0.58
    '))
    -0.57
    "])
    -0.56
    Tazama
    -0.54
    hasia
    -0.54
     BoxDecoration
    -0.54
     Apel
    -0.53
    hols
    -0.53
    Geplaatst
    -0.52
    POSITIVE LOGITS
    出版年
    0.56
     Seeder
    0.55
     vektör
    0.51
    RESUMO
    0.48
    Šaltiniai
    0.48
    WebElementEntity
    0.47
    ArrowToggle
    0.46
    iausi
    0.46
     vectores
    0.46
    Ivoire
    0.46
    Activations Density 1.302%

    No Known Activations