© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 3857
    Prev
    Next
    INDEX
    Explanations

    the word "Google" and immediately following words

    oai_token-act-pair · gemini-2.0-flash

    Google

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/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.18.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     propOrder
    -0.66
    Slf
    -0.55
    InjectAttribute
    -0.52
     صوتيه
    -0.47
    autique
    -0.46
     intStringLen
    -0.45
    ء
    -0.43
    квар
    -0.43
     final
    -0.42
    djangoproject
    -0.42
    POSITIVE LOGITS
    estacks
    0.66
     autorytatywna
    0.65
     {},
    0.61
     MessageBoxIcon
    0.60
     iſt
    0.57
     Kaur
    0.57
    OOTDTY
    0.56
    fromnode
    0.55
     StatefulWidget
    0.55
    enfone
    0.54
    Activations Density 1.526%

    No Known Activations