© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 7133
    Prev
    Next
    INDEX
    Explanations

    present tense forms of "to be."

    oai_token-act-pair · gemini-2.0-flash

    sentence fragments

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    adə
    -0.53
     entendu
    -0.48
    coso
    -0.47
    naire
    -0.47
    жели
    -0.46
    mathop
    -0.46
    toplankton
    -0.46
    eabouts
    -0.46
    -0.45
     Growth
    -0.45
    POSITIVE LOGITS
    \{\\
    0.67
    transQ
    0.64
     estimés
    0.58
     disambiguazione
    0.57
    MessageTagHelper
    0.56
     AssemblyTitle
    0.55
    WriteBarrier
    0.54
    turbo
    0.53
     IMDG
    0.53
    BeginInit
    0.53
    Activations Density 0.666%

    No Known Activations