© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 1846
    Prev
    Next
    INDEX
    Explanations

    parts of words and names, especially of non-English origin

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     J
    -0.45
    <0x9C>
    -0.44
     von
    -0.42
     (
    -0.42
     We
    -0.41
     B
    -0.41
     porte
    -0.41
     g
    -0.41
     event
    -0.41
     begin
    -0.41
    POSITIVE LOGITS
    ########.
    1.00
     uſed
    0.90
     itſelf
    0.90
     raiſ
    0.89
     unſ
    0.88
    contentLoaded
    0.88
    RegressionTest
    0.88
     Efq
    0.86
    ValueStyle
    0.85
     EconPapers
    0.84
    Activations Density 6.096%

    No Known Activations