© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 474
    Prev
    Next
    INDEX
    Explanations

    words and punctuation related to dialog

    oai_token-act-pair · gemini-2.0-flash

    yes

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     myſelf
    -0.81
    Hentet
    -0.80
    thâu
    -0.79
     leaſt
    -0.77
     ſind
    -0.75
     iſt
    -0.75
     themſelves
    -0.75
     crdi
    -0.74
    ArgsConstructor
    -0.73
     reaſon
    -0.73
    POSITIVE LOGITS
     yes
    0.81
     Yes
    0.73
     YES
    0.65
    yes
    0.65
    Yes
    0.63
    YES
    0.63
     Yep
    0.54
    yep
    0.53
    Yep
    0.53
     Yeah
    0.47
    Activations Density 0.649%

    No Known Activations