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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 4762
    Prev
    Next
    INDEX
    Explanations

    Java code importing "android.os.Bundle", "android.support.v7.app"

    oai_token-act-pair · gemini-2.0-flash

    Bundle

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     فريبيس
    -1.16
    RenderAtEndOf
    -1.12
    SpringBootTest
    -1.09
    rungsseite
    -1.02
     يتيمه
    -1.02
     vPvB
    -0.99
    contentLoaded
    -0.97
     مرئيه
    -0.96
    
    -0.95
     disambiguazione
    -0.94
    POSITIVE LOGITS
    i
    0.71
    e
    0.68
    ↵
    0.63
     the
    0.63
    o
    0.61
    er
    0.60
    .
    0.58
      
    0.58
     while
    0.58
    a
    0.56
    Activations Density 0.260%

    No Known Activations