© 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. 8311
    Prev
    Next
    INDEX
    Explanations

    references to figures and tables in scientific publications

    oai_token-act-pair · gemini-2.0-flash

    figure, table, fig

    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
    ↵↵↵
    -0.59
    ]-->
    -0.48
    }\\
    -0.45
    ↵↵↵↵↵
    -0.45
    arum
    -0.43
    لينكات
    -0.43
    ↵↵↵↵
    -0.42
    ämään
    -0.42
    ↵↵↵↵↵↵↵
    -0.41
     juridiques
    -0.41
    POSITIVE LOGITS
    RegressionTest
    0.87
    HasForeignKey
    0.76
     старости
    0.75
     kasarigan
    0.73
    RunAsync
    0.71
    IVEREF
    0.71
     springfox
    0.70
    Geplaatst
    0.68
     Chwiliwch
    0.68
    expandindo
    0.66
    Activations Density 0.455%

    No Known Activations