© 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. 3964
    Prev
    Next
    INDEX
    Explanations

    clauses contrasting observed vs expected behavior or finding percentages or rates of events.

    oai_token-act-pair · gemini-2.0-flash

    small amount

    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
    :✨
    -0.66
    المناصب
    -0.62
     nahilalakip
    -0.61
     TextInputType
    -0.60
     OFDb
    -0.57
     defStyleAttr
    -0.57
     crossorigin
    -0.56
    RTDA
    -0.54
    crollView
    -0.52
     ModelExpression
    -0.51
    POSITIVE LOGITS
     minimal
    1.14
    minimal
    1.05
     meager
    1.04
    Minimal
    1.02
     scant
    1.01
     scanty
    1.01
     meagre
    1.00
    few
    0.96
     tiny
    0.96
     barely
    0.96
    Activations Density 3.112%

    No Known Activations