© 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. 4993
    Prev
    Next
    INDEX
    Explanations

    code snippets related to routing, serialization and XML manipulation

    oai_token-act-pair · gemini-2.0-flash

    Code 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
     Goode
    -0.52
    BlockPos
    -0.52
    xen
    -0.51
    zigen
    -0.49
     Florian
    -0.49
    ัด
    -0.49
    verwijspagina
    -0.49
    TagMode
    -0.49
    bufio
    -0.49
     Curtis
    -0.48
    POSITIVE LOGITS
     sạn
    0.57
     الحره
    0.56
    Activité
    0.54
     referenties
    0.50
     democrá
    0.49
    ględ
    0.48
    netbeans
    0.47
     jsPsych
    0.47
     sumpay
    0.47
    WithEmail
    0.46
    Activations Density 0.762%

    No Known Activations