© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 3816
    Prev
    Next
    INDEX
    Explanations

    the word "Quick" and possibly the word "bulk"

    oai_token-act-pair · gemini-2.0-flash

    coding/technical documentation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/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.18.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     event
    -0.77
    event
    -0.68
     e
    -0.63
    e
    -0.60
    EventArgs
    -0.59
    preventDefault
    -0.54
     EventArgs
    -0.53
     Event
    -0.53
     eventdata
    -0.53
     target
    -0.52
    POSITIVE LOGITS
    wegg
    0.59
    XmlEnum
    0.58
    Portail
    0.58
    yti
    0.57
    poro
    0.57
     jspb
    0.56
    Clik
    0.55
    FormTagHelper
    0.55
     ressemb
    0.55
    JsonInclude
    0.54
    Activations Density 0.505%

    No Known Activations