© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 5094
    Prev
    Next
    INDEX
    Explanations

    short words like "a," "the," "one," and "xi" in an Asian language (likely Chinese) context, mixed with some English words.

    oai_token-act-pair · gemini-2.0-flash

    technical text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     a
    -0.49
    vle
    -0.44
    cshtml
    -0.43
    tiple
    -0.43
     an
    -0.42
     dudas
    -0.42
     notificaciones
    -0.41
    Personensuche
    -0.40
    bitkan
    -0.40
     geha
    -0.40
    POSITIVE LOGITS
    awtextra
    0.79
    TagMode
    0.77
     transfieras
    0.73
    verwijspagina
    0.68
    Хьажоргаш
    0.68
    ыгана
    0.67
     raiſ
    0.67
    最快更新
    0.66
    ValueStyle
    0.64
     unknownFields
    0.64
    Activations Density 0.844%

    No Known Activations