© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 15194
    Prev
    Next
    INDEX
    Explanations

    proper nouns, including people, places, and organizations

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
     (
    -0.46
     same
    -0.45
     but
    -0.45
    y
    -0.44
    pero
    -0.44
     r
    -0.43
    ros
    -0.43
     k
    -0.42
     t
    -0.42
     u
    -0.42
    POSITIVE LOGITS
     propOrder
    1.09
    ArrowToggle
    0.99
    Personensuche
    0.97
     InputDecoration
    0.97
     Roskov
    0.93
     Савезне
    0.93
    InjectAttribute
    0.91
    SBATCH
    0.91
    UserScript
    0.90
    astéroïdes
    0.90
    Activations Density 4.255%

    No Known Activations