© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 14459
    Prev
    Next
    INDEX
    Explanations

    words related to observation, especially from satellites

    oai_token-act-pair · gemini-2.0-flash

    Satellites, space, and weather

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    DBNull
    -0.60
     gynnwys
    -0.59
    daging
    -0.58
    aarrggbb
    -0.57
    UnifiedTopology
    -0.56
    EOUT
    -0.56
    ReusableCell
    -0.54
     aleg
    -0.54
    clusal
    -0.54
     utafitiHapana
    -0.53
    POSITIVE LOGITS
     Wikimedijinoj
    0.68
    Билгалдахарш
    0.60
    EndProject
    0.60
     esternos
    0.59
    urlpatterns
    0.56
     DW
    0.53
     Pois
    0.51
     Swarm
    0.51
    Искәрмәләр
    0.50
    eventbus
    0.48
    Activations Density 1.676%

    No Known Activations