© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-GEMMASCOPE-TRANSCODER-16K
    7. 15202
    Prev
    Next
    INDEX
    Explanations

    words relating to blame, investigation, justification, or marriage

    oai_token-act-pair · gemini-2.0-flash

    Software related terms

    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
    other
    -1.88
     other
    -1.86
    autre
    -1.74
     autre
    -1.67
     another
    -1.67
    Other
    -1.64
     Other
    -1.62
    OTHER
    -1.60
     OTHER
    -1.57
    another
    -1.57
    POSITIVE LOGITS
    featureID
    0.52
    WebVitals
    0.50
    \|^{
    0.49
    angdong
    0.49
    PyExc
    0.47
    enderror
    0.47
     arşivlendi
    0.46
    erevan
    0.46
    addGap
    0.46
    énario
    0.46
    Activations Density 0.930%

    No Known Activations