© 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. 7145
    Prev
    Next
    INDEX
    Explanations

    a wide variety of common words in the English language, with seemingly no clear pattern or exclusion.

    oai_token-act-pair · gemini-2.0-flash

    Quantities

    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
    InitVars
    -0.96
    Everything
    -0.87
     Everything
    -0.84
    dafx
    -0.83
    expandindo
    -0.82
    tagHelperRunner
    -0.81
     ostavi
    -0.79
    zzleHttp
    -0.79
    __;
    -0.78
     ISNI
    -0.76
    POSITIVE LOGITS
     each
    1.21
     all
    1.01
    each
    0.93
     any
    0.82
    all
    0.79
    Each
    0.66
     Each
    0.65
    EACH
    0.62
    any
    0.60
     none
    0.60
    Activations Density 8.923%

    No Known Activations