© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 9997
    Prev
    Next
    INDEX
    Explanations

    words and symbols related to chemistry, biology/genetics, and scientific measurement

    oai_token-act-pair · gemini-2.0-flash

    Scientific language/references

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     كومونز
    -1.01
    )"),
    -0.89
     للمعارف
    -0.85
    tanleria
    -0.83
    enterOuterAlt
    -0.83
     ExecuteAsync
    -0.82
     ویکی‌پدیای
    -0.82
    saraba
    -0.80
     ?>>
    -0.80
     iprot
    -0.77
    POSITIVE LOGITS
     sako
    0.42
    info
    0.40
    пта
    0.39
    gamma
    0.37
    S
    0.36
     thiệu
    0.36
    旁
    0.36
     rato
    0.35
    ent
    0.35
    sum
    0.35
    Activations Density 2.688%

    No Known Activations