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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 24-GEMMASCOPE-TRANSCODER-16K
    4. 7864
    Prev
    Next
    INDEX
    Explanations

    C# code that uses `System.Collections.Generic`

    oai_token-act-pair · gemini-2.0-flash

    code

    np_max-act-logits · 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
     ſtate
    -0.83
     pleaſure
    -0.79
     referenties
    -0.77
     houſe
    -0.76
     raiſ
    -0.73
    penuhi
    -0.72
     Jefus
    -0.72
     Houſe
    -0.72
     Chriftian
    -0.71
     purpoſe
    -0.71
    POSITIVE LOGITS
    までも
    0.32
    Specialized
    0.31
     knotted
    0.29
     '\\;'
    0.29
     munt
    0.29
    angliski
    0.29
    :✨
    0.29
     Scalars
    0.28
    synchronize
    0.28
    samples
    0.28
    Activations Density 0.463%

    No Known Activations