© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 15355
    Prev
    Next
    INDEX
    Explanations

    phrases related to writing comments online

    oai_token-act-pair · gemini-2.0-flash

    unusual or archaic spellings

    np_token-act-pair-logits · gpt-4o-mini

    talking

    np_max-act-logits · gemini-2.0-flash
    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
    Negative Logits
    bu
    -0.50
    чо
    -0.45
     createStore
    -0.44
    idin
    -0.41
    zir
    -0.40
    面
    -0.40
    cel
    -0.38
    bat
    -0.37
    عي
    -0.37
    пли
    -0.37
    POSITIVE LOGITS
     Савезне
    0.92
     whoſe
    0.87
    SpringBootTest
    0.81
     Majefty
    0.81
    ArrowToggle
    0.78
     themſelves
    0.78
     propOrder
    0.78
     Shakspeare
    0.78
    siębior
    0.77
     Monfieur
    0.77
    Activations Density 14.691%

    No Known Activations