© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 2065
    Prev
    Next
    INDEX
    Explanations

    phrases relating to product performance, scientific reports, or corporate disclaiming responsibility

    oai_token-act-pair · gemini-2.0-flash

    news reports

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    出版年
    -0.61
     للمعارف
    -0.60
    bootstrapcdn
    -0.59
     références
    -0.57
     насељу
    -0.56
    קישורים
    -0.56
     Hobson
    -0.52
     apon
    -0.52
    araus
    -0.50
     impediment
    -0.49
    POSITIVE LOGITS
     تضيفلها
    0.74
    ChildIndex
    0.71
    OCCURRED
    0.66
    forChild
    0.65
    Билгалдахарш
    0.61
    المناصب
    0.59
    CppMethod
    0.58
    期刊论文
    0.58
    GenerationType
    0.57
    StatusBadRequest
    0.57
    Activations Density 5.551%

    No Known Activations