© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 6638
    Prev
    Next
    INDEX
    Explanations

    sentences discussing American football

    oai_token-act-pair · gemini-2.0-flash

    sports reporting

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    ValueStyle
    -0.62
    躇
    -0.59
    ViewFeatures
    -0.59
    awtextra
    -0.58
    transQ
    -0.57
    DockStyle
    -0.56
    textAppearance
    -0.56
    tagHelperRunner
    -0.56
    xion
    -0.55
    httphttps
    -0.55
    POSITIVE LOGITS
    ArrowToggle
    0.54
     popoli
    0.53
    Condol
    0.52
     scoperta
    0.51
     réfrig
    0.49
     élect
    0.48
     hydrauli
    0.48
     polaire
    0.48
    årige
    0.47
     violenza
    0.47
    Activations Density 1.614%

    No Known Activations