© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 3840
    Prev
    Next
    INDEX
    Explanations

    a jumble of domain-specific terms related to equations, scientific studies, and possibly a markup language.

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    WebServlet
    -0.58
    więcej
    -0.57
     hígado
    -0.54
    ("/:
    -0.54
    ($__
    -0.53
     éclat
    -0.52
     المعيارى
    -0.52
    Cubit
    -0.51
    SerializeField
    -0.50
     clés
    -0.50
    POSITIVE LOGITS
     backdrop
    0.83
     background
    0.83
     floor
    0.78
     base
    0.73
     backgrounds
    0.73
    ."]
    0.72
    floor
    0.66
     substrate
    0.66
     bottom
    0.65
    基
    0.65
    Activations Density 1.195%

    No Known Activations