© 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. 13461
    Prev
    Next
    INDEX
    Explanations

    words related to military rank, branches, and war

    oai_token-act-pair · gemini-2.0-flash

    Government officials

    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
     Mayor
    -1.09
     Coach
    -1.08
     President
    -1.05
     Professor
    -1.04
     Professors
    -1.02
     Прези
    -1.00
     Profesor
    -0.99
     Plaintiff
    -0.98
    President
    -0.97
     Judge
    -0.97
    POSITIVE LOGITS
     president
    0.52
     vice
    0.47
    ifrance
    0.42
     बजाय
    0.40
    ziali
    0.39
    bronn
    0.39
     secretary
    0.38
    ceum
    0.38
     utafitiHapana
    0.38
    räge
    0.37
    Activations Density 4.816%

    No Known Activations