© 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. 3152
    Prev
    Next
    INDEX
    Explanations

    C code related to the ngx library, particularly dealing with events, timers, and logging.

    oai_token-act-pair · gemini-2.0-flash

    archaic or unusual spelling patterns

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

    code

    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
     non
    -0.57
     the
    -0.57
     I
    -0.54
    ↵
    -0.54
     how
    -0.54
     says
    -0.51
     C
    -0.51
    ,
    -0.50
     true
    -0.50
     sebanyak
    -0.50
    POSITIVE LOGITS
     myſelf
    0.91
     uſed
    0.90
     Monfieur
    0.80
     faſt
    0.79
     Efq
    0.75
     uſe
    0.75
     itſelf
    0.75
     ſy
    0.75
     uſ
    0.73
     auffi
    0.72
    Activations Density 7.212%

    No Known Activations