© 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. 1051
    Prev
    Next
    INDEX
    Explanations

    a mix of numbers, airplane parts, and a few words in a Slavic language

    oai_token-act-pair · gemini-2.0-flash

    Variants of "so"

    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
     transférez
    -0.70
    =$?
    -0.67
    ioutil
    -0.63
    ittäin
    -0.62
     cioè
    -0.59
     endregion
    -0.57
     Efq
    -0.57
    φέρει
    -0.56
    BeginContext
    -0.55
     MediaType
    -0.55
    POSITIVE LOGITS
     so
    1.95
    so
    1.30
    So
    0.98
     So
    0.97
     så
    0.93
     так
    0.82
     SO
    0.81
     così
    0.77
    如此
    0.75
    那麼
    0.70
    Activations Density 1.279%

    No Known Activations