© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 2767
    Prev
    Next
    INDEX
    Explanations

    phrases concerning constraints or maximum capacity

    oai_token-act-pair · gemini-2.0-flash

    exceed

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    protoimpl
    -0.72
     محفوظة
    -0.55
     onCreateView
    -0.54
     kasarigan
    -0.51
    énario
    -0.49
    PositiveButton
    -0.49
    XmlAccessType
    -0.48
    NegativeButton
    -0.48
     makeStyles
    -0.48
     ύ
    -0.48
    POSITIVE LOGITS
     exceeded
    1.01
     exceed
    0.98
     exceeds
    0.92
    ex
    0.91
    Ex
    0.89
     exceeding
    0.88
    超
    0.86
     Ex
    0.85
    EX
    0.84
     übers
    0.77
    Activations Density 1.800%

    No Known Activations