© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 13248
    Prev
    Next
    INDEX
    Explanations

    instances where something is referred to or cited, especially academic references

    oai_token-act-pair · gemini-2.0-flash

    refer

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     чтоб
    -0.65
     которое
    -0.62
    djangoproject
    -0.61
    いかがでしたか
    -0.60
    完成です
    -0.58
    )))),
    -0.57
    当店
    -0.56
     K
    -0.56
     пожалуйста
    -0.54
     Park
    -0.53
    POSITIVE LOGITS
    AddTagHelper
    0.97
    tvguidetime
    0.94
    脚注の使い方
    0.80
    matchCondition
    0.76
    Diwedd
    0.74
    IsMutable
    0.73
     ciudadana
    0.73
    KommentareTeilen
    0.73
     كومونز
    0.69
     Dispatch
    0.69
    Activations Density 2.126%

    No Known Activations