© 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. 5263
    Prev
    Next
    INDEX
    Explanations

    characters that are part of JSON formatting

    oai_token-act-pair · gemini-2.0-flash

    specific programming syntax or characters

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

    say "quotation mark"

    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
     '
    -0.63
    num
    -0.59
    top
    -0.58
     D
    -0.57
    _
    -0.57
    ('
    -0.55
     ‘
    -0.55
     F
    -0.55
    f
    -0.55
     
    -0.55
    POSITIVE LOGITS
     ویکی‌پدیای
    0.98
    Cordialement
    0.92
     itſelf
    0.91
     myſelf
    0.88
    NUMX
    0.85
     crdi
    0.85
     Houſe
    0.85
    endphp
    0.84
     auffi
    0.83
     ſtate
    0.82
    Activations Density 3.031%

    No Known Activations