© 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. 13118
    Prev
    Next
    INDEX
    Explanations

    speech from experts

    oai_token-act-pair · gemini-2.0-flash

    disagreement

    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
    oa̍t
    -0.60
    qrstuvwxyz
    -0.57
    omock
    -0.56
    RegressionTest
    -0.50
    허
    -0.50
     ویکی‌پدی
    -0.49
    Closer
    -0.49
    bedien
    -0.49
     ok
    -0.48
     OK
    -0.48
    POSITIVE LOGITS
     beg
    0.85
     dispute
    0.82
     disagree
    0.81
     counters
    0.76
     discord
    0.75
     contesting
    0.73
     disputes
    0.69
     contradict
    0.69
     contest
    0.68
     {},
    0.68
    Activations Density 1.534%

    No Known Activations