© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 4553
    Prev
    Next
    INDEX
    Explanations

    negative sentiment words and the phrase "common sense"

    oai_token-act-pair · gemini-2.0-flash

    sense

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
    SourceChecksum
    -0.61
     Chwiliwch
    -0.54
    JoinTable
    -0.48
    CreateMap
    -0.46
     henne
    -0.46
     "
    -0.44
    PRWEB
    -0.43
    setViewportView
    -0.42
     acque
    -0.42
    ParallelGroup
    -0.41
    POSITIVE LOGITS
    SharedDtor
    0.88
     idiot
    0.82
    smart
    0.81
     smart
    0.78
     Smart
    0.77
    Smart
    0.73
     smartly
    0.73
     foolish
    0.71
     Idiot
    0.71
     stupid
    0.71
    Activations Density 0.787%

    No Known Activations