© 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. 11497
    Prev
    Next
    INDEX
    Explanations

    mentions of statistics and data related to countries

    oai_token-act-pair · gemini-2.0-flash

    International statistics

    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
     Re
    -0.45
     mo
    -0.45
    a
    -0.42
     Mo
    -0.42
     te
    -0.42
     R
    -0.41
    prepareStatement
    -0.41
     eg
    -0.40
     N
    -0.40
     a
    -0.39
    POSITIVE LOGITS
     myſelf
    0.87
     ब्रेकडाउन
    0.82
     ſta
    0.79
     crdi
    0.77
     Efq
    0.76
     verſ
    0.76
     abſ
    0.75
     paff
    0.73
     Fitur
    0.73
     pleaſure
    0.73
    Activations Density 0.353%

    No Known Activations