© 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. 7342
    Prev
    Next
    INDEX
    Explanations

    references to legal codes and statutes

    oai_token-act-pair · gemini-2.0-flash

    say period

    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
     متعلقه
    -0.99
    StructEnd
    -0.88
     Мексичка
    -0.86
     gynhyrchwyd
    -0.85
     виправивши
    -0.80
    новниш
    -0.78
    mybatisplus
    -0.76
    WaitGroup
    -0.74
     Normdatei
    -0.73
     poffe
    -0.73
    POSITIVE LOGITS
    RefreshLayout
    0.48
    вича
    0.39
    buses
    0.36
    perror
    0.36
    Przypisy
    0.36
     Pis
    0.35
    ARSE
    0.35
    uper
    0.35
     £
    0.34
     P
    0.33
    Activations Density 1.208%

    No Known Activations