© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 13921
    Prev
    Next
    INDEX
    Explanations

    the word "up", especially in the phrasal verb "clean up", and also some C++ code structures.

    oai_token-act-pair · gemini-2.0-flash

    up

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     Sch
    -0.53
    scriptcase
    -0.52
     sch
    -0.50
    Articolo
    -0.49
     Car
    -0.48
    venta
    -0.46
     Ka
    -0.46
     su
    -0.45
    Embrace
    -0.45
    inol
    -0.45
    POSITIVE LOGITS
     AssemblyCulture
    0.94
    tvguidetime
    0.84
    Rhestr
    0.83
     disambiguazione
    0.79
    ImageContext
    0.71
     فريبيس
    0.69
     vectorielle
    0.68
    RuleContext
    0.67
     مشين
    0.66
    icals
    0.66
    Activations Density 0.131%

    No Known Activations