© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 13636
    Prev
    Next
    INDEX
    Explanations

    discourse markers and conjunctions, especially including the word "even"

    oai_token-act-pair · gemini-2.0-flash

    even

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    ंदीखरीदारी
    -0.71
     investissements
    -0.65
     démocr
    -0.65
     avoient
    -0.63
     kaarangay
    -0.63
     nôtre
    -0.63
    StoreMessageInfo
    -0.62
     initComponents
    -0.62
     myſelf
    -0.61
    hésite
    -0.60
    POSITIVE LOGITS
     if
    0.59
    Scénario
    0.57
     ca
    0.54
     sc
    0.52
    Invoke
    0.50
    DoubleQuotes
    0.49
     as
    0.49
    WebMethod
    0.49
    ря
    0.48
     Part
    0.48
    Activations Density 11.224%

    No Known Activations