© 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. 4861
    Prev
    Next
    INDEX
    Explanations

    phrases indicating new information or viewpoints, often related to legal or academic contexts.

    oai_token-act-pair · gemini-2.0-flash

    Gaining support or traction

    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
    ModelAdmin
    -0.66
    tagHelper
    -0.58
    最快更新
    -0.57
    ValueStyle
    -0.57
    BeginContext
    -0.57
    PyExc
    -0.56
    ftagPool
    -0.56
    JspWriter
    -0.54
     مشين
    -0.54
    tagext
    -0.52
    POSITIVE LOGITS
     edge
    0.66
    脚注の使い方
    0.59
     }}"></
    0.57
    edge
    0.57
     foothold
    0.56
    లాలు
    0.54
    condu
    0.54
     scope
    0.53
     sustenance
    0.53
    VIAF
    0.53
    Activations Density 2.465%

    No Known Activations