© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 5238
    Prev
    Next
    INDEX
    Explanations

    code snippets related to Android development, including XML layouts and Java/Kotlin code interacting with Android UI elements.

    oai_token-act-pair · gemini-2.0-flash

    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_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
    atola
    -0.49
    Alle
    -0.41
     Pol
    -0.40
     dormitorios
    -0.38
     abbra
    -0.38
     nur
    -0.37
    estima
    -0.37
     alle
    -0.36
    Or
    -0.36
     esca
    -0.35
    POSITIVE LOGITS
    saraba
    1.02
    BeginInit
    0.89
    makeConstraints
    0.86
     intptr
    0.84
     onAnimation
    0.82
    ConstraintMaker
    0.77
    SourceChecksum
    0.77
    :✨
    0.73
    ValueStyle
    0.72
     propOrder
    0.70
    Activations Density 1.579%

    No Known Activations