© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 12310
    Prev
    Next
    INDEX
    Explanations

    nuanced discussions of life and death

    oai_token-act-pair · gemini-2.0-flash

    life experiences

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     fathoms
    -0.79
     opérés
    -0.79
    MLLoader
    -0.73
     pellic
    -0.72
    ConstraintMaker
    -0.71
     pleaſure
    -0.69
    FormTagHelper
    -0.69
     Roskov
    -0.67
     Shakspeare
    -0.67
     Reverso
    -0.66
    POSITIVE LOGITS
     Ma
    0.56
     ma
    0.54
    cor
    0.51
    Ma
    0.48
     Sa
    0.47
     cor
    0.47
     ("
    0.47
    はじめに
    0.47
    io
    0.46
    ong
    0.46
    Activations Density 7.424%

    No Known Activations