© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 5160
    Prev
    Next
    INDEX
    Explanations

    sequences of numbers, especially those representing statistics like yards, numerical IDs, or temperatures

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     ser
    -0.52
     đáo
    -0.42
    }")
    -0.41
     wor
    -0.41
     
    -0.40
     har
    -0.40
    r
    -0.39
     cor
    -0.38
    eslint
    -0.38
     bes
    -0.38
    POSITIVE LOGITS
     समीक्षाओं
    0.84
     Administrativna
    0.84
     betweenstory
    0.77
    three
    0.77
     igång
    0.76
     للمعارف
    0.73
     trois
    0.73
    THREE
    0.73
    AutoScale
    0.72
     devriez
    0.72
    Activations Density 25.341%

    No Known Activations