© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 10781
    Prev
    Next
    INDEX
    Explanations

    the word "bar" in code and test files, along with related keywords like "test", "all", and "Qu".

    oai_token-act-pair · gemini-2.0-flash

    bar

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     proto
    -0.57
     Goff
    -0.56
    ILON
    -0.56
     Jeb
    -0.56
     sensi
    -0.56
     bub
    -0.52
     tap
    -0.52
     Kett
    -0.51
     port
    -0.51
     red
    -0.51
    POSITIVE LOGITS
    VideoCapture
    0.83
     nahilalakip
    0.82
    Chham
    0.79
     noDo
    0.74
    Personendaten
    0.74
     propOrder
    0.72
     enfans
    0.71
    featureID
    0.70
    لينكات
    0.70
     referenties
    0.68
    Activations Density 1.343%

    No Known Activations