© 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. 6454
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to governments, budgets, documents, and politics.

    oai_token-act-pair · gemini-2.0-flash

    taken/stolen

    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
     taking
    -0.84
    Autoritní
    -0.77
    Taking
    -0.76
     Taking
    -0.75
    aarrggbb
    -0.74
    taking
    -0.74
     ExecuteAsync
    -0.73
    tagHelperRunner
    -0.66
    ArgsConstructor
    -0.66
    smithy
    -0.64
    POSITIVE LOGITS
     taken
    0.98
     Taken
    0.78
    taken
    0.73
     TAKEN
    0.73
     stolen
    0.67
    Taken
    0.64
    acquired
    0.55
     Acquired
    0.50
     performing
    0.49
     acquired
    0.49
    Activations Density 8.706%

    No Known Activations