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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 3337
    Prev
    Next
    INDEX
    Explanations

    C programming code related to defining classes, opcodes, tracing, and memory pools

    oai_token-act-pair · gemini-2.0-flash

    escape sequences or backslashes

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

    )

    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
    ↵
    -1.33
    <eos>
    -0.75
    //
    -0.60
    </b>
    -0.54
    AsUp
    -0.47
    …
    -0.47
    rawDesc
    -0.47
    SequentialGroup
    -0.46
    ...
    -0.46
    -0.45
    POSITIVE LOGITS
     \
    1.56
    \
    1.35
     \

    1.23
    ,\
    1.01
    .\
    1.00
    ()\
    0.96
    >\
    0.95
    !\
    0.94
    )\
    0.94
    \

    0.94
    Activations Density 2.472%
    No Known Activations