© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 11121
    Prev
    Next
    INDEX
    Explanations

    code punctuation, specifically commas, semicolons, and parentheses

    oai_token-act-pair · gemini-2.0-flash

    Code and equations

    np_max-act-logits · gemini-2.0-flash

    punctuation

    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_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
     La
    -0.51
    ギュ
    -0.50
    Mediabestanden
    -0.47
    glise
    -0.46
     Bu
    -0.46
    Enciclopedia
    -0.44
     Leach
    -0.44
     Bear
    -0.44
     ph
    -0.44
    nion
    -0.43
    POSITIVE LOGITS
    parsedMessage
    0.79
     InputDecoration
    0.78
    ukone
    0.73
     ―――――
    0.73
     Efq
    0.68
     ſche
    0.66
     Anſ
    0.66
     AttributeSet
    0.66
     للمعارف
    0.65
     doubtnut
    0.65
    Activations Density 1.737%

    No Known Activations