© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 16050
    Prev
    Next
    INDEX
    Explanations

    words and phrases from business/technical writing that focus on what something does, how to do something, or that something is good/useful.

    oai_token-act-pair · gemini-2.0-flash

    organizations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    下载附件
    -0.71
     متعلقه
    -0.71
    AddTagHelper
    -0.66
    Jîn
    -0.60
     Theſe
    -0.60
     ivelany
    -0.58
     fufficient
    -0.58
     JpaRepository
    -0.57
     BoxFit
    -0.56
    ^(@)
    -0.56
    POSITIVE LOGITS
     businesses
    0.73
     organizations
    0.65
     users
    0.64
     owners
    0.63
     companies
    0.63
     organisations
    0.60
     governments
    0.58
     corporations
    0.57
     even
    0.55
     brands
    0.55
    Activations Density 3.385%

    No Known Activations