© 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. 833
    Prev
    Next
    INDEX
    Explanations

    incomplete words where only the beginning of the string is captured

    oai_token-act-pair · gemini-2.0-flash

    contains "il"

    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
    RegressionTest
    -0.71
    openzeppelin
    -0.68
     betweenstory
    -0.68
    DeleteBehavior
    -0.67
     MenuView
    -0.66
    存于互联网档案馆
    -0.64
    CompilerServices
    -0.63
     createSlice
    -0.59
     nahilalakip
    -0.58
    Παραπομπές
    -0.57
    POSITIVE LOGITS
     il
    1.10
    Il
    0.98
     Il
    0.97
     ill
    0.94
     Ill
    0.93
     IL
    0.93
    Ill
    0.90
    ILL
    0.89
     Illinois
    0.87
    ill
    0.86
    Activations Density 0.233%

    No Known Activations