© 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. 12336
    Prev
    Next
    INDEX
    Explanations

    pronouns and common words in romance languages like Portuguese, Spanish, and French

    oai_token-act-pair · gemini-2.0-flash

    Romance language articles

    np_max-act-logits · gemini-2.0-flash
    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
     समीक्षाओं
    -0.63
    transQ
    -0.61
     propOrder
    -0.57
     متعلقه
    -0.56
    
    -0.52
    bnf
    -0.51
    Portail
    -0.51
     AssemblyProduct
    -0.50
    piac
    -0.50
     محفوظة
    -0.50
    POSITIVE LOGITS
     lo
    1.36
     le
    1.14
     τον
    1.02
     το
    0.90
     l
    0.85
     την
    0.81
     го
    0.79
     LO
    0.77
     la
    0.72
    Lo
    0.71
    Activations Density 0.314%

    No Known Activations