© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 1675
    Prev
    Next
    INDEX
    Explanations

    the word "quest" when the user is having trouble with it and needs to "complete" it, also related to playing a "game."

    oai_token-act-pair · gemini-2.0-flash

    terms related to game mechanics

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

    video games

    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
    Negative Logits
     NSCoder
    -0.56
    forRoot
    -0.55
    }()
    -0.55
    Personendaten
    -0.52
     DriverManager
    -0.51
    Datuak
    -0.51
     itſelf
    -0.50
     Halley
    -0.50
     Abstr
    -0.48
    GEBURTSDATUM
    -0.47
    POSITIVE LOGITS
    Affirmed
    0.59
    хьтан
    0.54
    ExecuteReader
    0.54
     customise
    0.52
    sneak
    0.52
    ματο
    0.51
    level
    0.51
     rejoindre
    0.50
     level
    0.49
     customizing
    0.49
    Activations Density 1.895%

    No Known Activations