© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 3334
    Prev
    Next
    INDEX
    Explanations

    mathematical terms related to data analysis and linear algebra

    oai_token-act-pair · gemini-2.0-flash

    singular

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     surla
    -0.71
    gemeinden
    -0.62
    invokeLater
    -0.60
     اكتوبر
    -0.59
     manquante
    -0.59
     leto
    -0.56
     Manning
    -0.55
     חיצוניים
    -0.55
     الحره
    -0.55
    prechpartner
    -0.54
    POSITIVE LOGITS
     Administrativna
    0.65
    بوابة
    0.65
     useNavigate
    0.63
    MessageDigest
    0.61
     Мексичка
    0.59
    DispatchToProps
    0.57
    NTSTATUS
    0.57
     PDC
    0.56
    CompleteListener
    0.56
     tastes
    0.56
    Activations Density 4.028%

    No Known Activations