© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 5264
    Prev
    Next
    INDEX
    Explanations

    the abbreviation for the United States, "U.S."

    oai_token-act-pair · gemini-2.0-flash

    US references

    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
     createState
    -0.70
     initComponents
    -0.69
     contextLoads
    -0.69
     دیکھیے
    -0.69
     سكانية
    -0.68
    Lähteet
    -0.68
    ViewFeatures
    -0.65
    parsedMessage
    -0.63
    Composable
    -0.63
    StructEnd
    -0.63
    POSITIVE LOGITS
     للمعارف
    0.50
    RP
    0.45
     aéri
    0.44
    IX
    0.44
    tu
    0.44
    ON
    0.43
    bal
    0.42
    널
    0.41
    DC
    0.41
    MV
    0.41
    Activations Density 0.689%

    No Known Activations