© 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. 3111
    Prev
    Next
    INDEX
    Explanations

    references to historical events or technical procedures, which often include dates, numbers and the use of "to be."

    oai_token-act-pair · gemini-2.0-flash

    be

    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
    Not in Any Lists

    No Comments

    Negative Logits
    BASEPATH
    -0.57
    Referenties
    -0.51
     SafeArea
    -0.50
     smtplib
    -0.50
    WinForms
    -0.50
    StringVar
    -0.50
     onItemClick
    -0.50
    menuStrip
    -0.49
    ThroughAttribute
    -0.49
    SPATH
    -0.48
    POSITIVE LOGITS
     be
    1.89
     être
    1.60
     быть
    1.48
     essere
    1.46
     být
    1.45
     being
    1.45
     been
    1.41
     бути
    1.37
     być
    1.27
    being
    1.19
    Activations Density 10.920%

    No Known Activations