© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 4046
    Prev
    Next
    INDEX
    Explanations

    numbers

    oai_token-act-pair · gemini-2.0-flash

    words with specific language patterns, possibly French

    np_token-act-pair-logits · gpt-4o-mini

    numbers in various contexts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    NOPQRST
    -0.56
    tionnaire
    -0.50
    essary
    -0.50
    PerformLayout
    -0.50
     kasarigan
    -0.50
    ⓧ
    -0.49
    IDES
    -0.49
     St
    -0.47
    MENTE
    -0.47
    nthesis
    -0.47
    POSITIVE LOGITS
     kaarangay
    0.66
    saraba
    0.65
     pandémie
    0.65
    StoreMessageInfo
    0.65
     hâte
    0.62
     abstrato
    0.59
     magasiner
    0.59
     supérieurs
    0.58
     beginnetje
    0.57
     brancas
    0.57
    Activations Density 4.138%

    No Known Activations