© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 13923
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "that" and similar pronouns, possibly coupled with words with some kind of sentiment.

    oai_token-act-pair · gemini-2.0-flash

    That

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    انگلیسی
    -0.43
    WhereInput
    -0.39
     bhi
    -0.38
    DMETHOD
    -0.38
    cibly
    -0.37
     iNdEx
    -0.37
    Similarly
    -0.37
     čet
    -0.37
     THOUGHTS
    -0.36
     useAppContext
    -0.36
    POSITIVE LOGITS
     autorytatywna
    0.92
    InjectAttribute
    0.77
    [](
    0.71
     initComponents
    0.71
    Autoritní
    0.66
    ViewFeatures
    0.65
     juges
    0.64
     Diman
    0.63
     resourceCulture
    0.61
     StatefulWidget
    0.60
    Activations Density 1.682%

    No Known Activations