© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 11845
    Prev
    Next
    INDEX
    Explanations

    Spanish words that translate to "the" and "you", particularly "lo", "la", and "te"

    oai_token-act-pair · gemini-2.0-flash

    te

    np_max-act · gemini-2.0-flash

    Spanish clitics

    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_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
    <bos>
    -0.79
     ब्रेकडाउन
    -0.56
    useState
    -0.47
    Ign
    -0.47
    chet
    -0.46
     \
    -0.45
    д
    -0.44
     Paglinawan
    -0.44
    JAXB
    -0.43
     AssemblyProduct
    -0.43
    POSITIVE LOGITS
     îi
    0.77
     يتيمه
    0.68
    Història
    0.68
    EDEFAULT
    0.68
     MaterialApp
    0.65
     CascadeType
    0.64
    HtmlAttribute
    0.64
     esportivo
    0.63
    ollectionView
    0.62
    Lieferumfang
    0.61
    Activations Density 0.380%

    No Known Activations