© 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. 1813
    Prev
    Next
    INDEX
    Explanations

    dates and times including related prepositions like "after"

    oai_token-act-pair · gemini-2.0-flash

    Events and dates

    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
     mû
    -0.50
    tilhe
    -0.47
     lunghi
    -0.46
    ीय
    -0.45
     démocr
    -0.44
     rst
    -0.44
     brancas
    -0.44
     consiguiente
    -0.43
     sumpay
    -0.43
    zaki
    -0.43
    POSITIVE LOGITS
    GEBURTSDATUM
    1.02
     referenties
    1.01
    BeginContext
    0.73
    ScopeManager
    0.71
    */),
    0.60
    nocache
    0.58
    WriteBarrier
    0.57
    MemoryWarning
    0.57
    complexContent
    0.57
    })^
    0.57
    Activations Density 3.813%

    No Known Activations