© 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
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 3838
    Prev
    Next
    INDEX
    Explanations

    spanish words mixed in with code or links

    oai_token-act-pair · gemini-2.0-flash

    translations of "and"

    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
    ądź
    -0.61
    tagext
    -0.60
    zeczytaj
    -0.54
     voulais
    -0.53
     saludo
    -0.50
    mandu
    -0.50
     parlent
    -0.49
     quelcon
    -0.49
    łom
    -0.48
     treno
    -0.48
    POSITIVE LOGITS
     en
    2.38
     En
    1.69
    En
    1.68
     EN
    1.25
    en
    1.02
     én
    0.98
     i
    0.94
     y
    0.87
     ett
    0.78
     Ena
    0.77
    Activations Density 1.621%

    No Known Activations