© 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. 1382
    Prev
    Next
    INDEX
    Explanations

    words that are possibly Croatian

    oai_token-act-pair · gemini-2.0-flash

    foreign languages

    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
    PSON
    -0.49
    ÓN
    -0.48
    ORTS
    -0.48
    ber
    -0.48
    chan
    -0.47
    ASING
    -0.47
    loo
    -0.47
    CCESS
    -0.47
    erv
    -0.46
    tuig
    -0.46
    POSITIVE LOGITS
     Medea
    0.49
     xenia
    0.46
     Babylonian
    0.45
     tetanus
    0.45
     Athenians
    0.44
     Etrus
    0.44
     shewn
    0.43
     slalom
    0.42
     Shakspeare
    0.42
     Phry
    0.42
    Activations Density 0.558%

    No Known Activations