© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 8501
    Prev
    Next
    INDEX
    Explanations

    the word "addition," and in some cases the words "apart" or "too"

    oai_token-act-pair · gemini-2.0-flash

    addition

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    fillType
    -0.59
    ✎
    -0.54
    RegressionTest
    -0.53
     parcour
    -0.53
    ">',
    -0.53
    trav
    -0.52
    laston
    -0.52
    ramentas
    -0.48
    consulté
    -0.48
    adə
    -0.47
    POSITIVE LOGITS
     الحره
    0.73
    lapsingToolbar
    0.72
     Pyrr
    0.68
     TextAppearance
    0.68
     MonoBehaviour
    0.67
     DevComponents
    0.67
     Schweitzer
    0.66
    oudoune
    0.65
    ρών
    0.65
     onResponse
    0.64
    Activations Density 0.446%

    No Known Activations