© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 15500
    Prev
    Next
    INDEX
    Explanations

    Spanish words and programming-related terms, especially those used together

    oai_token-act-pair · gemini-2.0-flash

    Spanish words

    np_max-act-logits · gemini-2.0-flash

    Spanish

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     Krakowie
    -0.79
    ływ
    -0.71
    quantidade
    -0.69
    ỡi
    -0.68
    atual
    -0.67
     Geral
    -0.65
     Și
    -0.65
     Etter
    -0.64
    linha
    -0.63
    muito
    -0.63
    POSITIVE LOGITS
     con
    0.61
     y
    0.59
     ya
    0.57
     el
    0.57
     una
    0.57
     las
    0.57
     en
    0.54
     los
    0.52
     como
    0.52
     que
    0.49
    Activations Density 2.300%

    No Known Activations