© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 12271
    Prev
    Next
    INDEX
    Explanations

    segments of code

    oai_token-act-pair · gemini-2.0-flash

    code formatting and syntax elements

    np_token-act-pair-logits · gpt-4o-mini

    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_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     llorar
    -0.49
    parsedMessage
    -0.44
    cmd
    -0.44
     @"/
    -0.43
    ViewFeatures
    -0.41
     Superhosts
    -0.41
     fatale
    -0.41
     postales
    -0.40
     Witkin
    -0.38
     faciles
    -0.38
    POSITIVE LOGITS
    ]--;
    0.88
     للمعارف
    0.81
    setupUi
    0.80
    ")));
    0.77
    cotch
    0.73
    "}")
    0.71
     تانيه
    0.70
     مرئيه
    0.69
    orianCalendar
    0.68
    úgó
    0.66
    Activations Density 0.781%

    No Known Activations