© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 11516
    Prev
    Next
    INDEX
    Explanations

    Java and C++ code snippets

    oai_token-act-pair · gemini-2.0-flash

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    AndEndTag
    -0.93
    webElementXpaths
    -0.84
    WebVitals
    -0.81
    FormTagHelper
    -0.79
    jsdelivr
    -0.74
    bootstrapcdn
    -0.71
    findpost
    -0.70
    PerformLayout
    -0.67
    "])
    -0.64
     NSCoder
    -0.63
    POSITIVE LOGITS
     communautés
    0.50
    ThroughAttribute
    0.49
     bestemt
    0.48
     esist
    0.47
     Layla
    0.45
     étan
    0.43
     Burnet
    0.43
     diante
    0.42
     liik
    0.41
     mohair
    0.41
    Activations Density 3.490%

    No Known Activations