© 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. 1011
    Prev
    Next
    INDEX
    Explanations

    terms related to programming and computer administration

    oai_token-act-pair · gemini-2.0-flash

    Questions and problems

    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
    ConstraintMaker
    -0.73
     onAnimation
    -0.67
     florales
    -0.63
     magnétique
    -0.61
     murale
    -0.60
     eléctricas
    -0.60
     elettrica
    -0.60
     maschile
    -0.59
     veneta
    -0.59
     alimentare
    -0.58
    POSITIVE LOGITS
    jspx
    0.65
     huge
    0.58
     different
    0.56
     amazing
    0.55
     awesome
    0.54
     hilarious
    0.52
     incredible
    0.52
     innocent
    0.52
     extraordinary
    0.52
     impressive
    0.52
    Activations Density 0.460%

    No Known Activations