© 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. 4926
    Prev
    Next
    INDEX
    Explanations

    Dutch words, especially those beginning with "De", and references to research grants or organizations

    oai_token-act-pair · gemini-2.0-flash

    Code and configuration files

    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
    ix
    -0.51
    je
    -0.49
    Der
    -0.46
    ian
    -0.44
     aç
    -0.43
    ure
    -0.43
    Je
    -0.43
     Damit
    -0.42
    der
    -0.42
    rin
    -0.41
    POSITIVE LOGITS
     initComponents
    0.88
     protoimpl
    0.73
    __":
    0.68
    ^(@)
    0.67
    viewDidLoad
    0.62
     propOrder
    0.57
    __":
    0.56
    skjaer
    0.56
     defaultstate
    0.56
     defStyle
    0.56
    Activations Density 0.028%

    No Known Activations