© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 9773
    Prev
    Next
    INDEX
    Explanations

    programming-related terms, especially from the Javascript and SQL languages, and potentially including Spanish words related to programming

    oai_token-act-pair · gemini-2.0-flash

    foreign words

    np_max-act-logits · gemini-2.0-flash

    say "▁"

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     del
    -1.07
    del
    -0.82
     el
    -0.75
     DEL
    -0.69
     de
    -0.67
    Del
    -0.63
     della
    -0.63
     Del
    -0.62
     dels
    -0.61
     dell
    -0.60
    POSITIVE LOGITS
     o
    1.02
     о
    0.65
     Monfieur
    0.63
     octopus
    0.60
     Jefus
    0.60
     او
    0.59
     Brasileiro
    0.59
     Shakspeare
    0.58
     Theſe
    0.57
     oa
    0.56
    Activations Density 0.281%

    No Known Activations