© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6118
    Prev
    Next
    INDEX
    Explanations

    words related to keeping things, such as remembering passwords or staying connected

    oai_token-act-pair · gemini-2.0-flash

    words related to managing tasks or updates

    np_token-act-pair-logits · gpt-4o-mini

    Stay connected or active

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    hålla
    -0.54
     Engaging
    -0.53
     Inspiring
    -0.51
    arko
    -0.48
    threatening
    -0.48
    breaking
    -0.48
    AndEndTag
    -0.47
    全文
    -0.47
    graceful
    -0.47
    growing
    -0.46
    POSITIVE LOGITS
     turned
    0.81
     pulled
    0.75
     converted
    0.75
     extracted
    0.74
     transformed
    0.71
     solved
    0.71
     settled
    0.71
     boosted
    0.70
    complexContent
    0.70
     edited
    0.70
    Activations Density 1.881%

    No Known Activations