© 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. 10209
    Prev
    Next
    INDEX
    Explanations

    negations and exceptions using the word "not" or similar words

    oai_token-act-pair · gemini-2.0-flash

    everyone

    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
    mybatisplus
    -0.60
     архивлан
    -0.48
     typelib
    -0.48
    toplankton
    -0.45
    thenia
    -0.44
    protoc
    -0.44
     unwit
    -0.42
    XPATH
    -0.41
    rdquo
    -0.41
     Besøkt
    -0.41
    POSITIVE LOGITS
     everyone
    1.86
    everyone
    1.73
     everybody
    1.68
     all
    1.62
     Everyone
    1.59
    Everyone
    1.58
    everybody
    1.57
     Everybody
    1.52
     EVERYONE
    1.52
    Everybody
    1.47
    Activations Density 1.669%

    No Known Activations