© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 9248
    Prev
    Next
    INDEX
    Explanations

    the word "above" and also seems to activate on names and recipes

    oai_token-act-pair · gemini-2.0-flash

    Code/Documentation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     سكانية
    -0.82
     disambiguazione
    -0.78
     متعلقه
    -0.76
     autorytatywna
    -0.73
    labus
    -0.70
    GEBURTSDATUM
    -0.69
    Demografía
    -0.68
     initComponents
    -0.68
    parsedMessage
    -0.66
     officiers
    -0.65
    POSITIVE LOGITS
    ArgsConstructor
    0.46
     cantit
    0.42
     siguran
    0.42
     lucru
    0.41
     obicei
    0.39
    存于互联网档案馆
    0.38
     hay
    0.38
     kambing
    0.37
     actual
    0.37
    actual
    0.36
    Activations Density 1.348%

    No Known Activations