© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 7144
    Prev
    Next
    INDEX
    Explanations

    code snippets related to Android layouts

    oai_token-act-pair · gemini-2.0-flash

    Android layout properties

    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
    Negative Logits
    __":
    -0.58
     Genti
    -0.51
     parcela
    -0.51
    cagon
    -0.50
     sound
    -0.50
    iosk
    -0.49
     kasarigan
    -0.49
     getRule
    -0.48
    libri
    -0.48
    SetBool
    -0.48
    POSITIVE LOGITS
    versite
    0.54
    AFE
    0.53
    ChildIndex
    0.49
    κτηρισ
    0.49
    kologi
    0.43
    ptid
    0.43
    queryInterface
    0.43
    salm
    0.43
    ★★★★☆
    0.43
    фикация
    0.41
    Activations Density 0.429%

    No Known Activations