© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 3-GEMMASCOPE-TRANSCODER-16K
    7. 5931
    Prev
    Next
    INDEX
    Explanations

    code snippets, mathematical equations, and XML-like tags.

    oai_token-act-pair · gemini-2.0-flash

    code syntax

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
    enumi
    -0.60
    ]--;
    -0.58
    ]='\
    -0.53
    +#+#
    -0.52
    JvmStatic
    -0.52
    _{*}
    -0.52
    AMIL
    -0.51
    SuccessListener
    -0.51
    >())
    -0.51
    ₡
    -0.51
    POSITIVE LOGITS
    <bos>
    0.97
     MainAxisSize
    0.58
    createServer
    0.55
     doInBackground
    0.55
     <<<
    0.54
     contextLoads
    0.54
    PyErr
    0.54
    StructEnd
    0.53
    WriteBarrier
    0.52
    rawDesc
    0.52
    Activations Density 3.632%

    No Known Activations