© 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. 9141
    Prev
    Next
    INDEX
    Explanations

    a mix of Arabic characters with some other symbols and numbers, possibly related to encoding or formatting

    oai_token-act-pair · gemini-2.0-flash

    non-english and file paths

    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
    σθαι
    -0.48
    "।
    -0.42
    
    -0.41
     Trọng
    -0.39
     fraude
    -0.38
    ০
    -0.36
     fathoms
    -0.36
    waters
    -0.36
    heets
    -0.36
    ãn
    -0.35
    POSITIVE LOGITS
     maxn
    0.49
     EINVAL
    0.48
    ientôt
    0.45
    ēd
    0.44
    وأضاف
    0.44
    NameInMap
    0.44
    anskje
    0.44
     AppColors
    0.44
     NDEBUG
    0.44
     pylint
    0.43
    Activations Density 1.144%

    No Known Activations