© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 13705
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to medical procedures, test taking and study

    oai_token-act-pair · gemini-2.0-flash

    technical/scientific documents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    četně
    -0.52
     durumda
    -0.51
     chré
    -0.50
    rededor
    -0.49
     myſelf
    -0.49
     habet
    -0.48
     zufolge
    -0.48
    mejores
    -0.48
     themſelves
    -0.48
     Tunisie
    -0.47
    POSITIVE LOGITS
    MigrationBuilder
    0.77
     Paglinawan
    0.72
     betweenstory
    0.66
    :✨
    0.66
     odkazy
    0.65
    }))
    0.65
     OMITBAD
    0.65
    ArrowToggle
    0.65
    QMetaType
    0.62
     AttributeSet
    0.61
    Activations Density 1.313%

    No Known Activations