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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 1069
    Prev
    Next
    INDEX
    Explanations

    words or symbols related to Portugal

    oai_token-act-pair · gemini-2.0-flash

    Portugal/Brazil related

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     Portuguese
    -1.61
     Brazilian
    -1.54
     Ohio
    -1.48
     Brazil
    -1.47
     Portugal
    -1.30
    Ohio
    -1.30
    Portuguese
    -1.29
    Brazilian
    -1.27
    Brazil
    -1.22
     portug
    -1.22
    POSITIVE LOGITS
     CascadeType
    0.57
    tableFuture
    0.50
    GUILayout
    0.50
     Mittag
    0.48
     AttributeSet
    0.48
    TabIndex
    0.48
     suspensão
    0.48
    AxisAlignment
    0.47
    ẫy
    0.47
    shadowRadius
    0.46
    Activations Density 1.843%

    No Known Activations