© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 15564
    Prev
    Next
    INDEX
    Explanations

    words that frequently appear in scientific research papers

    oai_token-act-pair · gemini-2.0-flash

    terms related to experimental conditions

    np_token-act-pair-logits · gpt-4o-mini

    experimental conditions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/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.21.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    ReusableCell
    -0.71
    StoryboardSegue
    -0.64
     otomatig
    -0.61
    PyExc
    -0.59
    Geplaatst
    -0.57
     propOrder
    -0.54
    NameInMap
    -0.54
    EndContext
    -0.54
     esboço
    -0.53
    TemporalType
    -0.53
    POSITIVE LOGITS
     conditions
    0.79
     Conditions
    0.71
     optimisation
    0.70
     optimization
    0.69
     condition
    0.68
     experiments
    0.67
     experimental
    0.67
    条件
    0.63
     experiment
    0.62
     optimized
    0.62
    Activations Density 8.421%

    No Known Activations