© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 12552
    Prev
    Next
    INDEX
    Explanations

    names of Chinese people and organizations involved in science or technology

    oai_token-act-pair · gemini-2.0-flash

    scientific papers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    OrNil
    -0.63
     betweenstory
    -0.56
     numberOfRows
    -0.53
     dAtA
    -0.50
     marred
    -0.50
    Personendaten
    -0.48
    Или
    -0.46
    toso
    -0.46
     "..\..\
    -0.46
    äsident
    -0.46
    POSITIVE LOGITS
    thâu
    0.51
     Z
    0.51
     Lulu
    0.51
    osuke
    0.50
    huahua
    0.48
    inhua
    0.48
    culoskeletal
    0.48
     &___
    0.48
    Sui
    0.47
    atguigu
    0.47
    Activations Density 12.552%

    No Known Activations