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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 11859
    Prev
    Next
    INDEX
    Explanations

    what appears to be words or fragments of words in languages other than English that use different characters

    oai_token-act-pair · gemini-2.0-flash

    foreign language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     representatives
    -0.65
     representative
    -0.61
     composed
    -0.60
    mybatisplus
    -0.60
     domestiques
    -0.58
    もちゃ
    -0.58
     médicaux
    -0.58
     créations
    -0.56
     defaultstate
    -0.56
    +#+
    -0.56
    POSITIVE LOGITS
    titleMargin
    0.63
    webElementXpaths
    0.60
     autorytatywna
    0.57
     оригіналу
    0.56
    Chham
    0.54
    rdida
    0.51
    RenderAtEndOf
    0.50
    зулта
    0.48
    íncia
    0.48
    ]='\
    0.47
    Activations Density 13.679%

    No Known Activations