© 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. 3010
    Prev
    Next
    INDEX
    Explanations

    citation markers and possibly some numerical data

    oai_token-act-pair · gemini-2.0-flash

    numerical data and references

    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
    0
    -0.91
     zero
    -0.74
    ₀
    -0.73
    ０
    -0.72
    ০
    -0.61
     zéro
    -0.60
    
    -0.59
    CppCodeGen
    -0.58
     cero
    -0.58
     zeros
    -0.57
    POSITIVE LOGITS
     Meksiku
    0.58
     mxArray
    0.57
     kasarigan
    0.57
     apoptotic
    0.57
    GeneratedCode
    0.56
    flink
    0.56
    featureID
    0.56
    IUrlHelper
    0.55
    PARATUS
    0.55
     GenerationType
    0.54
    Activations Density 1.792%

    No Known Activations