© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 11886
    Prev
    Next
    INDEX
    Explanations

    various forms of instances, instantiated, and related text

    oai_token-act-pair · gemini-2.0-flash

    inst

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    atus
    -0.63
    ruct
    -0.54
    ΕΝ
    -0.51
     Pinot
    -0.51
     Prodi
    -0.51
     चीज़ों
    -0.50
    ATUS
    -0.49
     Satoshi
    -0.49
     Oscill
    -0.49
    cení
    -0.49
    POSITIVE LOGITS
     just
    2.08
    just
    1.85
    Just
    1.70
     Just
    1.70
     JUST
    1.48
     simply
    1.47
     juste
    1.36
    JUST
    1.29
     merely
    1.23
    simply
    1.22
    Activations Density 2.452%

    No Known Activations