© 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. 8055
    Prev
    Next
    INDEX
    Explanations

    text discussing adding or categorizing events on a webpage

    oai_token-act-pair · gemini-2.0-flash

    events

    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
    Not in Any Lists

    No Comments

    Negative Logits
    oredCriteria
    -0.65
     ffilmiau
    -0.64
    MessageTagHelper
    -0.63
    HasForeignKey
    -0.56
     estekak
    -0.55
    :],
    -0.55
    outWeight
    -0.54
    mybatisplus
    -0.52
    XXI
    -0.51
     ListTile
    -0.50
    POSITIVE LOGITS
     events
    1.03
     Events
    0.93
     event
    0.93
    events
    0.93
    Events
    0.87
     eventi
    0.84
     eventos
    0.81
    event
    0.81
     evento
    0.78
     EVENTS
    0.78
    Activations Density 1.233%

    No Known Activations