© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10085
    Prev
    Next
    INDEX
    Explanations

    personal and professional histories of people

    oai_token-act-pair · gemini-2.0-flash

    biographies

    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
    Not in Any Lists

    No Comments

    Negative Logits
     Bolshe
    -0.61
     téléchargez
    -0.60
     Annotated
    -0.60
     berço
    -0.59
     myſelf
    -0.59
    تقاوى
    -0.58
     Theſe
    -0.57
     giornal
    -0.56
    ſelf
    -0.56
     katze
    -0.56
    POSITIVE LOGITS
     en
    0.55
     worked
    0.54
     ph
    0.53
    Ārējās
    0.53
    RegressionTest
    0.51
     huyền
    0.51
    KommentareTeilen
    0.50
     agrí
    0.49
    ajas
    0.48
     sup
    0.48
    Activations Density 0.919%

    No Known Activations