© 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. 3904
    Prev
    Next
    INDEX
    Explanations

    words ending in 'ly' or containing 'pre'

    oai_token-act-pair · gemini-2.0-flash

    words ending in ly

    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
    Not in Any Lists

    No Comments

    Negative Logits
    toch
    -0.48
    irability
    -0.47
     Replacement
    -0.45
    GRANTED
    -0.45
     chàng
    -0.45
     lowest
    -0.44
    Urb
    -0.44
    eaky
    -0.44
     irré
    -0.44
     Examiners
    -0.44
    POSITIVE LOGITS
    setVerticalGroup
    0.79
     betweenstory
    0.73
    ActionMode
    0.73
     فريبيس
    0.72
    ArrowToggle
    0.71
    جستارهای
    0.71
     insuffisamment
    0.69
     otomatig
    0.69
     '\\;'
    0.67
     AssemblyCompany
    0.65
    Activations Density 1.332%

    No Known Activations