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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 15780
    Prev
    Next
    INDEX
    Explanations

    mentions of Argentina, football, Argentinian places, and football teams

    oai_token-act-pair · gemini-2.0-flash

    Argentina

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    libft
    -0.51
    EDEFAULT
    -0.48
    TabIndex
    -0.46
    able
    -0.45
    EnumMember
    -0.43
    evich
    -0.42
    UseVisualStyle
    -0.42
    HasBeenSet
    -0.41
     your
    -0.41
    Décès
    -0.40
    POSITIVE LOGITS
     BorderRadius
    0.72
    ########.
    0.68
     vectorielles
    0.65
    cửa
    0.63
     extérieurs
    0.63
     fermés
    0.63
     bezeichneter
    0.62
     démocr
    0.62
     scolaires
    0.62
     الحره
    0.61
    Activations Density 1.683%

    No Known Activations