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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 3545
    Prev
    Next
    INDEX
    Explanations

    uses of personal pronouns

    oai_token-act-pair · gemini-2.0-flash

    got

    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
     get
    -1.35
    get
    -1.07
     gets
    -1.06
     getting
    -0.93
     Get
    -0.83
    Get
    -0.74
     Getting
    -0.73
     Gets
    -0.70
    Getting
    -0.70
    getting
    -0.67
    POSITIVE LOGITS
    got
    1.08
    Got
    1.05
     got
    1.01
     Got
    0.95
     StatefulWidget
    0.80
    WireFormatLite
    0.74
     GOT
    0.74
    gota
    0.68
    GOT
    0.67
     gott
    0.65
    Activations Density 1.455%

    No Known Activations