© 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. 14206
    Prev
    Next
    INDEX
    Explanations

    code or programming terms in both English and Portuguese

    oai_token-act-pair · gemini-2.0-flash

    Portuguese words

    np_max-act · gemini-2.0-flash

    Portuguese/Spanish

    np_max-act-logits · gpt-5-mini
    Triggered by @chenshw0109
    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
    Negative Logits
    jména
    -0.58
    jScrollPane
    -0.54
    скоре
    -0.52
     őket
    -0.52
     pleaſure
    -0.51
     grunn
    -0.50
    FloatField
    -0.49
    でご
    -0.49
     miſ
    -0.49
     появились
    -0.48
    POSITIVE LOGITS
     становника
    0.95
    sidemargin
    0.91
    Hochspringen
    0.85
     Paints
    0.83
    ScopeManager
    0.83
    +#+#
    0.81
    Enllaces
    0.80
     protoimpl
    0.80
    thâu
    0.80
    ècie
    0.79
    Activations Density 0.167%

    No Known Activations