© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 13756
    Prev
    Next
    INDEX
    Explanations

    dates and related place names

    oai_token-act-pair · gemini-2.0-flash

    formal writing

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    MLLoader
    -0.69
     initComponents
    -0.62
    ArgumentParser
    -0.62
    RectangleBorder
    -0.59
     pauv
    -0.58
     bodyParser
    -0.57
     doInBackground
    -0.56
    permitAll
    -0.55
    ScopeManager
    -0.55
     ContentValues
    -0.54
    POSITIVE LOGITS
    Tembelea
    0.84
    EDEFAULT
    0.69
    bewerken
    0.50
     出版
    0.49
    UserScript
    0.49
     Handic
    0.48
    zeß
    0.47
     fro
    0.47
     rango
    0.46
    Seni
    0.46
    Activations Density 3.141%

    No Known Activations