© 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. 3683
    Prev
    Next
    INDEX
    Explanations

    things connected to a travel or leisure experience

    oai_token-act-pair · gemini-2.0-flash

    Experiences and Activities

    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
     experience
    -2.59
    experience
    -2.34
     Experience
    -2.33
    Experience
    -2.28
     EXPERIENCE
    -2.17
    EXPERIENCE
    -1.88
     expérience
    -1.86
     experiencia
    -1.74
    expérience
    -1.73
     experiência
    -1.70
    POSITIVE LOGITS
    makeConstraints
    0.73
     ब्रेकडाउन
    0.63
    FXML
    0.61
    WebElementEntity
    0.60
    はじめに
    0.56
     pinulongan
    0.55
     AppDelegate
    0.55
    ApplicationTests
    0.54
    PerformLayout
    0.54
    UnsafeEnabled
    0.52
    Activations Density 9.108%

    No Known Activations