© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 6170
    Prev
    Next
    INDEX
    Explanations

    code and code-related language

    oai_token-act-pair · gemini-2.0-flash

    code snippets

    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
     set
    -0.61
     r
    -0.54
     best
    -0.47
     Set
    -0.47
     setId
    -0.46
     file
    -0.45
     High
    -0.45
     Down
    -0.42
     h
    -0.41
     Ph
    -0.41
    POSITIVE LOGITS
    CloseOperation
    0.94
    ViewFeatures
    0.80
    AndEndTag
    0.79
     tdci
    0.78
     crdi
    0.73
    uxxxx
    0.72
    RectangleBorder
    0.71
    iastes
    0.71
     tfsi
    0.70
    reportWebVitals
    0.70
    Activations Density 4.329%

    No Known Activations