© 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. 1782
    Prev
    Next
    INDEX
    Explanations

    words related to conducting research and experiments, especially with medical or scientific data

    oai_token-act-pair · gemini-2.0-flash

    data collection parameters or fields

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

    technical/scientific text

    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
    PhysRev
    -0.79
    NameInMap
    -0.73
    Personensuche
    -0.72
    IsMutable
    -0.69
     HasFactory
    -0.69
    PyExc
    -0.69
     ModelExpression
    -0.65
    oredCriteria
    -0.65
    aarrggbb
    -0.63
    #+#
    -0.63
    POSITIVE LOGITS
    varande
    0.57
    ↵
    0.56
     adulte
    0.56
     traitements
    0.54
     traités
    0.54
     rechange
    0.54
     traité
    0.52
     enfance
    0.52
     esimer
    0.52
     besoins
    0.52
    Activations Density 20.502%

    No Known Activations