© 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. 11622
    Prev
    Next
    INDEX
    Explanations

    snippets of C code that check for heart or breathing problems and print the results in Portuguese

    oai_token-act-pair · gemini-2.0-flash

    non-standard tokens or specific identifiers

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

    a

    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
     myſelf
    -0.88
     Diſ
    -0.87
     themſelves
    -0.82
     greateſt
    -0.82
     Monfieur
    -0.81
     purpoſe
    -0.76
     Reſ
    -0.75
     Inſ
    -0.74
     Conſ
    -0.73
     pleaſure
    -0.73
    POSITIVE LOGITS
    thâu
    0.52
    Brainz
    0.51
    MessageTagHelper
    0.50
    цезда
    0.50
     '\\;'
    0.49
    TagHelper
    0.45
     AssemblyTitle
    0.45
    WriteAttribute
    0.45
    pfung
    0.44
     Orrell
    0.44
    Activations Density 2.160%

    No Known Activations