© 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. 15450
    Prev
    Next
    INDEX
    Explanations

    a mix of numbers and units, mathematical expressions, or formatting terms related to web design

    oai_token-act-pair · gemini-2.0-flash

    W/w

    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
    ugna
    -0.47
     HAPPENED
    -0.45
     pr
    -0.44
    ula
    -0.44
     cy
    -0.43
    gele
    -0.43
     sem
    -0.42
     ta
    -0.42
     sy
    -0.42
     S
    -0.42
    POSITIVE LOGITS
    W
    1.09
     W
    1.00
     w
    0.94
    w
    0.94
    Ｗ
    0.88
     WX
    0.87
    WA
    0.87
    𝑤
    0.86
     wd
    0.86
    wdata
    0.86
    Activations Density 2.466%

    No Known Activations