© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 12134
    Prev
    Next
    INDEX
    Explanations

    code syntax and related keywords.

    oai_token-act-pair · gemini-2.0-flash

    Code/language snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    -0.82
    Personendaten
    -0.81
    AsUp
    -0.78
    ]--;
    -0.77
    PerformLayout
    -0.77
    WindowConstants
    -0.73
    ειτουργ
    -0.69
    ^(@)
    -0.68
    kuuta
    -0.68
    AntiForgeryToken
    -0.68
    POSITIVE LOGITS
    withstanding
    0.45
    他要
    0.43
    <bos>
    0.41
    anggil
    0.39
    :][
    0.38
     Bunny
    0.37
    יהם
    0.37
     Weit
    0.37
     Thorn
    0.36
     connexes
    0.36
    Activations Density 3.007%

    No Known Activations