© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 1581
    Prev
    Next
    INDEX
    Explanations

    passages of technical writing with acronyms, symbols and abbreviations

    oai_token-act-pair · gemini-2.0-flash

    P

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     P
    -1.09
    P
    -0.90
     p
    -0.78
    setP
    -0.73
     getP
    -0.73
    getP
    -0.72
    Ｐ
    -0.65
     П
    -0.58
     AP
    -0.56
    RP
    -0.55
    POSITIVE LOGITS
    
    0.88
     configureStore
    0.70
     يتيمه
    0.65
     resourceCulture
    0.62
    ########.
    0.57
    inars
    0.57
    اقرأ
    0.57
     Riet
    0.56
    FunctionFlags
    0.56
     secondaire
    0.56
    Activations Density 2.341%

    No Known Activations