© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 7837
    Prev
    Next
    INDEX
    Explanations

    the word 'fly' and phrases with the word 'air', and some date related words

    oai_token-act-pair · gemini-2.0-flash

    dynamic movement

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     PhpStorm
    -0.70
     BrowserModule
    -0.69
     onCreateView
    -0.65
    rungsseite
    -0.63
     Bedürf
    -0.61
    dafx
    -0.58
    innerHeight
    -0.57
    enment
    -0.56
    NewGuid
    -0.55
     purpoſe
    -0.54
    POSITIVE LOGITS
    Népesség
    0.62
     بيها
    0.60
    CodeAttribute
    0.60
    parsedMessage
    0.59
    بوابة
    0.58
    MessageTagHelper
    0.55
    Autoritní
    0.54
    enschappelijke
    0.54
    addCriterion
    0.53
     autorytatywna
    0.53
    Activations Density 1.474%

    No Known Activations