© 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. 15477
    Prev
    Next
    INDEX
    Explanations

    technical documents describing mechanical parts or chemical compositions

    oai_token-act-pair · gemini-2.0-flash

    bearings lubrication

    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
    ╮
    -0.54
    phazard
    -0.53
     الحره
    -0.53
    DockStyle
    -0.52
    TestTools
    -0.50
    ]")]
    -0.50
     intptr
    -0.50
    anyeol
    -0.50
    uver
    -0.49
    setupUi
    -0.48
    POSITIVE LOGITS
    hoeddwyd
    0.58
     beginnetje
    0.54
    Chham
    0.52
    Identyfik
    0.51
    Datuak
    0.49
    InstrumentedTest
    0.49
    rungsseite
    0.49
    TestBed
    0.47
    RTSC
    0.47
     bearing
    0.47
    Activations Density 2.112%

    No Known Activations