© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 8-GEMMASCOPE-TRANSCODER-16K
    7. 4911
    Prev
    Next
    INDEX
    Explanations

    phrases related to academic research, medical conditions and performance or labor.

    oai_token-act-pair · gemini-2.0-flash

    from

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     مشين
    -0.69
    Teks
    -0.64
    //
    -0.64
    InstrumentedTest
    -0.61
    ResumeLayout
    -0.60
    حوالہ
    -0.59
    
    -0.59
    SpringBootTest
    -0.58
    /**
    -0.58
    itarianism
    -0.58
    POSITIVE LOGITS
    іга
    0.54
    unyai
    0.53
     beschik
    0.51
     mať
    0.49
    #!/
    0.48
    ิ้ง
    0.48
    исленность
    0.47
    rungsseite
    0.47
    持つ
    0.47
     dispozici
    0.47
    Activations Density 1.390%

    No Known Activations