© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 7-GEMMASCOPE-TRANSCODER-16K
    7. 11338
    Prev
    Next
    INDEX
    Explanations

    a combination of email addresses, math symbols, and chemistry symbols

    oai_token-act-pair · 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
    Not in Any Lists

    No Comments

    Negative Logits
    WebElementEntity
    -0.59
    Gambas
    -0.56
    ComponentName
    -0.56
    quiel
    -0.56
    zkod
    -0.53
    readAs
    -0.50
    spesies
    -0.49
    cerpts
    -0.49
    NavController
    -0.48
    RAINT
    -0.48
    POSITIVE LOGITS
     mattino
    0.66
     للمعارف
    0.63
    Autoritní
    0.59
     endwhile
    0.58
     vectorielles
    0.56
    <>();
    0.56
     насељу
    0.56
     بيها
    0.55
     antemano
    0.54
    basicConfig
    0.54
    Activations Density 0.811%

    No Known Activations