© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 15717
    Prev
    Next
    INDEX
    Explanations

    scientific text with mathematical expressions

    oai_token-act-pair · gemini-2.0-flash

    physics

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    utilisons
    -0.71
    rungsseite
    -0.64
    oplayer
    -0.60
     विश्वसनीयता
    -0.59
    PhysRevD
    -0.59
     initComponents
    -0.59
     transférez
    -0.58
     Taktlose
    -0.58
     noDo
    -0.57
    lccn
    -0.57
    POSITIVE LOGITS
    WithMany
    0.56
    ULER
    0.56
     Plane
    0.50
     AssemblyCompany
    0.44
    uler
    0.43
    arte
    0.43
    jig
    0.42
     plane
    0.41
    Plane
    0.41
    IER
    0.41
    Activations Density 6.289%

    No Known Activations