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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 3993
    Prev
    Next
    INDEX
    Explanations

    text that reports on sporting achievements, especially where multiple teams/players are listed

    oai_token-act-pair · gemini-2.0-flash

    Sports events

    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
     مشين
    -0.69
     won
    -0.59
    PerformLayout
    -0.56
     raggiung
    -0.54
    wenye
    -0.51
     spie
    -0.50
     تكبرها
    -0.50
    antMatchers
    -0.49
     otomatig
    -0.49
    |--
    -0.49
    POSITIVE LOGITS
     AssemblyCompany
    0.73
    ModelBuilder
    0.69
    XmlAccessorType
    0.61
    AntiForgeryToken
    0.61
    وفاته
    0.60
     BrowserModule
    0.57
    protoimpl
    0.54
    VersionUID
    0.53
    basicConfig
    0.53
     setInterval
    0.52
    Activations Density 5.767%

    No Known Activations