© 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
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 12521
    Prev
    Next
    INDEX
    Explanations

    things such as sports championships, competition, or chess competitions

    oai_token-act-pair · gemini-2.0-flash

    competitive sports

    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
     compete
    -1.93
     competition
    -1.93
     competing
    -1.79
     competes
    -1.76
    competition
    -1.76
     competed
    -1.71
     Competition
    -1.70
     competitors
    -1.70
    Competition
    -1.68
     competitor
    -1.66
    POSITIVE LOGITS
     שוליים
    0.66
    verwijspagina
    0.66
    SharedDtor
    0.64
     ProtoMessage
    0.60
    oa̍t
    0.59
    WithIOException
    0.57
    "?>
    0.57
    يكب
    0.57
    ($__
    0.57
    RegressionTest
    0.56
    Activations Density 2.165%

    No Known Activations