© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 5111
    Prev
    Next
    INDEX
    Explanations

    mentions of foundational or deeply entrenched concepts

    oai_token-act-pair · gemini-2.0-flash

    root

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
     تضيفلها
    -0.70
    ViewImports
    -0.66
    +#+
    -0.59
    CloseOperation
    -0.59
    awtextra
    -0.58
    ftagPool
    -0.58
     himo
    -0.57
    MemoryWarning
    -0.56
     cherchés
    -0.55
    xase
    -0.54
    POSITIVE LOGITS
     roots
    1.31
     Roots
    1.22
     root
    1.20
    roots
    1.16
    Roots
    1.10
     Root
    1.08
    root
    1.08
    Root
    1.06
    ROOT
    1.03
     rooted
    1.02
    Activations Density 0.829%

    No Known Activations