© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-GEMMASCOPE-TRANSCODER-16K
    7. 11306
    Prev
    Next
    INDEX
    Explanations

    words from different foreign languages including Portuguese, Spanish, and French

    oai_token-act-pair · gemini-2.0-flash

    Non-English snippets

    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
    createCanvas
    -0.77
    +#+#
    -0.72
    __":
    -0.68
     kaarangay
    -0.67
    lessly
    -0.63
    gnore
    -0.62
    rous
    -0.61
     eventdata
    -0.60
    MENAFN
    -0.60
    MLLoader
    -0.58
    POSITIVE LOGITS
     متعلقه
    0.59
     spē
    0.47
     traccia
    0.46
    ренко
    0.46
     DANG
    0.46
    jds
    0.46
     المعيارى
    0.46
     údaj
    0.45
    {:
    0.45
     Rated
    0.45
    Activations Density 6.394%

    No Known Activations