© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 3468
    Prev
    Next
    INDEX
    Explanations

    the prefix "trans"

    oai_token-act-pair · gemini-2.0-flash

    trans

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     Paglinawan
    -1.23
     Савезне
    -1.19
     NDEBUG
    -1.14
    ^(@)
    -1.08
     Meksiku
    -1.03
     AssemblyCulture
    -1.02
    PyExc
    -1.01
    новниш
    -1.00
     ویکی‌پدی
    -0.99
    AsUp
    -0.94
    POSITIVE LOGITS
     =
    0.70
    R
    0.68
      
    0.67
     
    0.66
    s
    0.65
    P
    0.65
    S
    0.63
    up
    0.63
    d
    0.62
    h
    0.61
    Activations Density 1.138%

    No Known Activations