© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 5864
    Prev
    Next
    INDEX
    Explanations

    code related to layouts in Android applications

    oai_token-act-pair · gemini-2.0-flash

    Android layouts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    StoryboardSegue
    -0.86
    "]];
    -0.85
    "])
    -0.85
    
    -0.85
     Italijanski
    -0.84
    "]]
    -0.83
    sizeCache
    -0.82
    bootstrapcdn
    -0.82
    AddTagHelper
    -0.81
    WebVitals
    -0.80
    POSITIVE LOGITS
     gidi
    0.45
    plus
    0.41
    .
    0.39
     dyr
    0.38
    off
    0.37
     confiance
    0.37
     segmented
    0.36
     hasard
    0.35
    Plus
    0.35
    ar
    0.34
    Activations Density 1.240%

    No Known Activations