© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 8578
    Prev
    Next
    INDEX
    Explanations

    code snippets in a programming language like Swift

    oai_token-act-pair · gemini-2.0-flash

    Code

    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
    AddTagHelper
    -0.85
    WebElementEntity
    -0.81
    GEBURTSDATUM
    -0.78
    Tembelea
    -0.76
    Personensuche
    -0.76
    RegressionTest
    -0.73
    зулта
    -0.71
     Infórmanos
    -0.71
     Мексичка
    -0.69
    IsContent
    -0.68
    POSITIVE LOGITS
    viewDidLoad
    0.56
    orro
    0.50
     nadzieję
    0.48
    UIApplication
    0.48
    mContext
    0.47
    UIT
    0.46
     امريكا
    0.44
    ignac
    0.44
    anyu
    0.44
    yordu
    0.44
    Activations Density 9.494%

    No Known Activations