© 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. 10733
    Prev
    Next
    INDEX
    Explanations

    mentions of swimming or spas

    oai_token-act-pair · gemini-2.0-flash

    swimming

    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
     apaixon
    -0.54
     Betracht
    -0.53
     hjel
    -0.53
     tasche
    -0.53
     aşk
    -0.52
     hjæl
    -0.52
     ortak
    -0.51
     liefde
    -0.51
    áže
    -0.51
     Konsequ
    -0.48
    POSITIVE LOGITS
     pageContext
    0.90
    RegressionTest
    0.85
     "..\..\..\
    0.82
    tvguidetime
    0.82
    IVEREF
    0.82
    DockStyle
    0.82
    LayoutStyle
    0.82
     ExecuteAsync
    0.79
    ----</
    0.78
    脚注の使い方
    0.76
    Activations Density 0.260%

    No Known Activations