© 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. 14786
    Prev
    Next
    INDEX
    Explanations

    the word "close" and derivatives in code and related text

    oai_token-act-pair · gemini-2.0-flash

    close

    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
     closing
    -1.78
     closed
    -1.67
     Closing
    -1.63
    Closing
    -1.62
     closure
    -1.61
     clos
    -1.60
    closing
    -1.59
     closes
    -1.56
     Closure
    -1.48
    closed
    -1.47
    POSITIVE LOGITS
     SUDOC
    0.42
    ]--;
    0.40
     Gould
    0.40
     Flucht
    0.40
    InitVars
    0.39
    undur
    0.38
    remacy
    0.37
     Pues
    0.37
     Verw
    0.37
     weichen
    0.37
    Activations Density 0.739%

    No Known Activations