© 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. 12198
    Prev
    Next
    INDEX
    Explanations

    code-related syntax such as braces, HTML tags, and CSS selectors

    oai_token-act-pair · gemini-2.0-flash

    words ending in "self"

    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
    ParallelGroup
    -0.57
    GeneratedValue
    -0.55
     <>",
    -0.52
     Gar
    -0.50
     '
    -0.50
     J
    -0.50
     Sch
    -0.49
    matchCondition
    -0.49
    rapp
    -0.49
    ATUM
    -0.49
    POSITIVE LOGITS
     itſelf
    0.75
     îna
    0.70
     deſt
    0.70
     fometimes
    0.69
     neceff
    0.67
     myſelf
    0.66
     fubject
    0.66
     télécharge
    0.64
     doraemon
    0.64
    ſelf
    0.62
    Activations Density 1.827%

    No Known Activations