© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 2425
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to keeping track in a notebook as well as words related values and lists.

    oai_token-act-pair · gemini-2.0-flash

    writing/digital content/business

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    ValueStyle
    -0.71
    GraphicsUnit
    -0.71
    osoma
    -0.59
    InjectAttribute
    -0.56
     >=",
    -0.56
    Trama
    -0.55
    出版年
    -0.54
    rschein
    -0.54
     يتيمه
    -0.53
    WEBPACK
    -0.53
    POSITIVE LOGITS
    nościo
    0.53
     {}\
    0.52
    ="/">
    0.50
     cương
    0.50
    tamount
    0.48
     menim
    0.46
    sega
    0.46
     Yugoslavia
    0.46
     lớp
    0.46
     Furious
    0.45
    Activations Density 3.841%

    No Known Activations