© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 13369
    Prev
    Next
    INDEX
    Explanations

    code snippets, particularly related to http responses, azure, and swift protobuf

    oai_token-act-pair · gemini-2.0-flash

    Code/error messages

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    存于互联网档案馆
    -0.61
     AssemblyProduct
    -0.53
    ']
    -0.52
    atoon
    -0.52
    '])
    -0.51
    onomía
    -0.51
    "]));
    -0.49
    ']],
    -0.49
     about
    -0.48
    Odkazy
    -0.48
    POSITIVE LOGITS
    RenderAtEndOf
    0.74
     виправивши
    0.73
    Демографія
    0.71
     Occasionally
    0.69
     Particularly
    0.63
    न्दर्भ
    0.62
     Notable
    0.62
     Notably
    0.61
     Especially
    0.61
    Occasionally
    0.59
    Activations Density 6.545%

    No Known Activations