© 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. 10828
    Prev
    Next
    INDEX
    Explanations

    expressions of emotion, especially in dialogue.

    oai_token-act-pair · gemini-2.0-flash

    interruptions or pauses

    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
     المعيارى
    -0.56
    ntry
    -0.49
    addi
    -0.48
     reported
    -0.47
     Seneca
    -0.47
    liy
    -0.46
    addRow
    -0.45
    相
    -0.45
     bk
    -0.45
    ว่า
    -0.45
    POSITIVE LOGITS
    endphp
    0.76
    Demografía
    0.69
     kasarigan
    0.62
     kaarangay
    0.61
     indisponible
    0.59
    tanleria
    0.58
    ьаж
    0.58
    Хьажоргаш
    0.56
    eschou
    0.55
    Errorf
    0.54
    Activations Density 1.042%

    No Known Activations