© 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. 7073
    Prev
    Next
    INDEX
    Explanations

    abbreviations, alphanumerics and initialisms usually used in scientific writing, such as database names or lab testing methods

    oai_token-act-pair · gemini-2.0-flash

    technical writing snippets

    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
     AssemblyCulture
    -0.71
    Personendaten
    -0.69
    تقاوى
    -0.53
     अपना
    -0.39
     pères
    -0.39
    קישורים
    -0.38
     régle
    -0.37
    RegressionTest
    -0.36
     vérit
    -0.36
     méta
    -0.36
    POSITIVE LOGITS
     Majefty
    0.76
     AssemblyTitle
    0.74
     Efq
    0.69
    "]];
    0.69
    ſelf
    0.69
    neſs
    0.66
     Houſe
    0.65
    
    0.65
     Conſ
    0.65
    ]};
    0.64
    Activations Density 9.284%

    No Known Activations