© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 1664
    Prev
    Next
    INDEX
    Explanations

    XML-like code related to memory components, parameters, and statistics, particularly DRAM and memory controller configurations

    oai_token-act-pair · gemini-2.0-flash

    terms related to self-referential language

    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
    Negative Logits
     N
    -1.52
     
    -1.51
     "
    -1.45
     A
    -1.42
     B
    -1.39
     M
    -1.38
     E
    -1.38
     P
    -1.37
     I
    -1.37
     S
    -1.37
    POSITIVE LOGITS
     itſelf
    2.50
     myſelf
    2.28
     ་་
    2.25
     pleaſure
    2.16
     Majefty
    2.14
     Efq
    2.09
     Monfieur
    2.09
     ―――――
    2.09
     Shakspeare
    2.08
    ſelf
    2.06
    Activations Density 6.822%

    No Known Activations