© 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. 2784
    Prev
    Next
    INDEX
    Explanations

    the fragment "de" and adjacent fragments

    oai_token-act-pair · gemini-2.0-flash

    de

    np_max-act · 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
     De
    -1.97
    De
    -1.89
     de
    -1.84
    de
    -1.52
     DE
    -1.31
     де
    -1.29
    DE
    -1.16
    デ
    -1.05
    Де
    -0.85
     DeV
    -0.82
    POSITIVE LOGITS
    aarrggbb
    0.89
    Tembelea
    0.86
     vectorielle
    0.85
    GEBURTSDATUM
    0.81
    StoryboardSegue
    0.77
     שוליים
    0.75
     vectorielles
    0.73
     hObject
    0.73
     financière
    0.73
     виправивши
    0.71
    Activations Density 3.448%

    No Known Activations