© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 23-GEMMASCOPE-TRANSCODER-16K
    7. 10313
    Prev
    Next
    INDEX
    Explanations

    words indicative of a sports game writeup.

    oai_token-act-pair · gemini-2.0-flash

    news and sports articles

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    CloseOperation
    -0.72
    )"),
    -0.65
     ""],
    -0.63
    "},
    -0.62
    "],
    -0.61
     ]
    -0.61
    ".
    -0.60
    }")
    -0.60
    ()))
    -0.60
    "]
    -0.60
    POSITIVE LOGITS
     ujednoznacz
    0.57
    writeField
    0.55
     RoutedEventArgs
    0.54
    addCriterion
    0.52
    sweat
    0.48
     bottom
    0.47
    ZIL
    0.47
    makeConstraints
    0.47
     Pass
    0.46
     snippetHide
    0.46
    Activations Density 1.295%

    No Known Activations