© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 2265
    Prev
    Next
    INDEX
    Explanations

    words about taking action that affects people

    oai_token-act-pair · gemini-2.0-flash

    marriage

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    msgTypes
    -0.57
     recrutement
    -0.50
    ylla
    -0.47
    lytes
    -0.47
    ARAN
    -0.47
    WaitGroup
    -0.47
    Generated
    -0.47
    logna
    -0.47
    edback
    -0.46
    ostringstream
    -0.46
    POSITIVE LOGITS
    RegressionTest
    0.69
    makeConstraints
    0.59
    rungsseite
    0.55
    AddTagHelper
    0.55
     ablaze
    0.54
    Koordinaten
    0.52
     ویکی‌پدی
    0.51
     behind
    0.51
    AnimationsModule
    0.49
     intact
    0.49
    Activations Density 19.105%

    No Known Activations