© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 9675
    Prev
    Next
    INDEX
    Explanations

    java programming language syntax for declaring variables and methods (or functions).

    oai_token-act-pair · gemini-2.0-flash

    Java and JSON code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    /***/
    -0.59
    RegistryLite
    -0.57
     ExecuteAsync
    -0.55
     resourceCulture
    -0.54
    cookieParser
    -0.51
     PLWABN
    -0.50
    GENERATED
    -0.49
    Aiheesta
    -0.49
     AppCompat
    -0.49
    Према
    -0.49
    POSITIVE LOGITS
    Luong
    0.54
    
    0.52
    `]
    0.49
    prnt
    0.49
     tập
    0.48
     aged
    0.47
     indexPath
    0.46
    servable
    0.46
     Teufel
    0.46
     опера
    0.46
    Activations Density 0.375%

    No Known Activations