© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 5458
    Prev
    Next
    INDEX
    Explanations

    a mix of words related to both prize-winning events and to US politics

    oai_token-act-pair · gemini-2.0-flash

    victory

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     won
    -1.82
    won
    -1.48
    Won
    -1.36
     Won
    -1.34
     WON
    -1.20
    WON
    -0.87
     winning
    -0.82
     winners
    -0.66
     winner
    -0.63
     gewann
    -0.63
    POSITIVE LOGITS
     win
    1.41
    Win
    1.14
     Win
    1.13
    win
    1.10
     WIN
    0.84
    WIN
    0.82
    RegressionTest
    0.80
    ViewImports
    0.65
    glMatrixMode
    0.60
    rikes
    0.59
    Activations Density 4.283%

    No Known Activations