© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 18-GEMMASCOPE-TRANSCODER-16K
    7. 4022
    Prev
    Next
    INDEX
    Explanations

    clauses describing causes or effects

    oai_token-act-pair · gemini-2.0-flash

    Unexpected events

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     experiment
    -1.79
     Experiment
    -1.63
     experiments
    -1.59
    Experiment
    -1.52
    experiment
    -1.48
     Experiments
    -1.39
     experimento
    -1.38
    EXPERIMENT
    -1.37
     EXPERIMENT
    -1.35
    Experiments
    -1.25
    POSITIVE LOGITS
    PRWEB
    0.56
     coming
    0.54
    లాలు
    0.53
     Coming
    0.52
    RegressionTest
    0.52
     varandra
    0.49
    ambung
    0.48
     solas
    0.48
     voraus
    0.47
    iestety
    0.47
    Activations Density 0.603%

    No Known Activations