© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 9811
    Prev
    Next
    INDEX
    Explanations

    words related to the scientific method and data collection, especially measurement and manipulation of variables

    oai_token-act-pair · gemini-2.0-flash

    Measurement/quantification/ordering

    np_max-act · gemini-2.0-flash

    quantity/number

    np_max-act-logits · gpt-5-mini
    Triggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     muualla
    -0.68
    ⃗
    -0.64
     متعلقه
    -0.62
     autorytatywna
    -0.57
    Espèce
    -0.57
    OrBuilder
    -0.54
    irsty
    -0.54
    proceed
    -0.51
     ['./
    -0.50
    bosis
    -0.49
    POSITIVE LOGITS
    GEBURTSDATUM
    0.67
     nahilalakip
    0.65
     number
    0.64
     length
    0.63
     time
    0.62
    ChildScrollView
    0.61
     size
    0.61
     amount
    0.57
    itone
    0.57
     value
    0.56
    Activations Density 2.591%

    No Known Activations