© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 5866
    Prev
    Next
    INDEX
    Explanations

    scientific and technical terms, especially acronyms and citations

    oai_token-act-pair · gemini-2.0-flash

    (

    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
     GenerationType
    -0.84
     CreateTagHelper
    -0.82
     Signalez
    -0.80
     للمعارف
    -0.75
    DockStyle
    -0.75
    UnusedPrivate
    -0.73
    Chham
    -0.71
     AssemblyCulture
    -0.71
    MessageTagHelper
    -0.70
     ویکی‌پدی
    -0.69
    POSITIVE LOGITS
     IG
    0.82
     IR
    0.81
     IM
    0.80
    IG
    0.79
    IH
    0.74
    IP
    0.74
    IB
    0.73
     IC
    0.73
    IR
    0.72
     IP
    0.72
    Activations Density 17.717%

    No Known Activations