© 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. 3619
    Prev
    Next
    INDEX
    Explanations

    results from women's sporting events that include times and distances

    oai_token-act-pair · gemini-2.0-flash

    technical programming keywords

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

    Athletics and 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_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
    <?
    -0.89
     myſelf
    -0.81
     Theſe
    -0.77
     Проци
    -0.75
    Portale
    -0.75
     disambiguazione
    -0.72
     itſelf
    -0.72
     themſelves
    -0.72
    Meik
    -0.72
    PerformLayout
    -0.71
    POSITIVE LOGITS
    ErrorListener
    0.55
     T
    0.48
     CreateTagHelper
    0.44
    andr
    0.43
    AND
    0.41
     Dynamic
    0.41
     N
    0.41
    T
    0.41
     And
    0.41
     AND
    0.41
    Activations Density 0.216%

    No Known Activations