© 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. 11846
    Prev
    Next
    INDEX
    Explanations

    equations and mathematical calculations.

    oai_token-act-pair · gemini-2.0-flash

    special characters and formatting markers

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

    code

    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
     \
    -1.53
    \
    -1.43
    .\
    -1.04
     \
    -1.04
    !\
    -1.01
    )\
    -0.97
    ,\
    -0.94
    :\
    -0.90
    ()\
    -0.86
    >\
    -0.85
    POSITIVE LOGITS
    ↵
    1.05
    AsUp
    0.60
    Itoa
    0.54
    //
    0.53
    GEBURTSDATUM
    0.52
    </b>
    0.52
     voluto
    0.50
    ?...
    0.50
    ]]
    0.49
    ');?>
    0.48
    Activations Density 5.698%

    No Known Activations