© 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. 3998
    Prev
    Next
    INDEX
    Explanations

    content warnings and disclaimers related to potentially offensive themes like violence, slavery, and non-consensual acts.

    oai_token-act-pair · gemini-2.0-flash

    ship

    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
    parsedMessage
    -0.89
    EndInit
    -0.84
    BeginInit
    -0.76
    InstrumentedTest
    -0.68
     EconPapers
    -0.68
     Normdatei
    -0.64
    styleType
    -0.61
    SharedDtor
    -0.59
     Orchid
    -0.58
     незавершена
    -0.58
    POSITIVE LOGITS
     ship
    1.20
    ship
    0.96
     ships
    0.95
     shipping
    0.94
     Ship
    0.91
    Ship
    0.88
     SHIP
    0.86
     shipper
    0.85
    shipping
    0.84
     shipped
    0.82
    Activations Density 0.580%

    No Known Activations