© 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. 1541
    Prev
    Next
    INDEX
    Explanations

    code snippets and math formulas, especially those containing the word "return," "output," or "value."

    oai_token-act-pair · gemini-2.0-flash

    value

    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
    تقاوى
    -1.33
     transfieras
    -1.06
     שוליים
    -1.06
     tartalomajánló
    -1.04
     للمعارف
    -1.02
     Мексичка
    -1.02
     nakalista
    -1.01
    fjspx
    -0.99
    脚注の使い方
    -0.99
     estimés
    -0.98
    POSITIVE LOGITS
     output
    0.75
    output
    0.69
     
    0.66
    -
    0.59
     return
    0.59
    Output
    0.57
    输出
    0.54
    .
    0.54
    c
    0.53
    getOutput
    0.53
    Activations Density 5.350%

    No Known Activations