© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 11784
    Prev
    Next
    INDEX
    Explanations

    words designating locations, people, and organizations, many in the context of sports, education and legal contexts, and references to time.

    oai_token-act-pair · gemini-2.0-flash

    specific identifiers or programming terms

    np_token-act-pair-logits · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     يتيمه
    -0.71
    AndEndTag
    -0.68
    GEBURTSDATUM
    -0.62
     Chwiliwch
    -0.58
     protoimpl
    -0.58
     Administrativna
    -0.58
    ClientSize
    -0.57
     kaarangay
    -0.57
    tisol
    -0.56
    Personendaten
    -0.56
    POSITIVE LOGITS
    adaptiveStyles
    0.54
    volut
    0.50
    ⓧ
    0.48
    原始内容存档于
    0.46
    stdafx
    0.46
    tableView
    0.45
    脚注の使い方
    0.43
    ấu
    0.42
    linspace
    0.42
    <<(
    0.42
    Activations Density 1.868%

    No Known Activations