© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 11736
    Prev
    Next
    INDEX
    Explanations

    code snippets with keywords or commands

    oai_token-act-pair · gemini-2.0-flash

    in or parentheses

    np_max-act · 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
     الحره
    -0.58
    /−
    -0.56
     להיות
    -0.55
    ])]
    -0.55
    Be
    -0.54
     be
    -0.54
     Be
    -0.53
     Pellegrini
    -0.53
    มาะ
    -0.52
    ocell
    -0.51
    POSITIVE LOGITS
    OGND
    0.82
     CreateTagHelper
    0.66
     propOrder
    0.64
     تضيفلها
    0.60
     împ
    0.57
     kuhusu
    0.57
     <>",
    0.54
     fraî
    0.53
    atshirt
    0.52
     Commentaires
    0.51
    Activations Density 2.959%

    No Known Activations