© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 12953
    Prev
    Next
    INDEX
    Explanations

    phrases related to planning or purpose

    oai_token-act-pair · gemini-2.0-flash

    intended

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    -0.91
     <>",
    -0.84
     autorytatywna
    -0.83
     houſe
    -0.79
    expandindo
    -0.79
     vPvB
    -0.76
     resourceCulture
    -0.75
     AssemblyCompany
    -0.74
    PyExc
    -0.73
    RefNanny
    -0.73
    POSITIVE LOGITS
     to
    0.78
    ToBe
    0.48
     να
    0.48
    to
    0.47
     себя
    0.46
    File
    0.40
    ToAdd
    0.40
     for
    0.40
     ho
    0.38
     o
    0.38
    Activations Density 0.744%

    No Known Activations