© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 11585
    Prev
    Next
    INDEX
    Explanations

    proper nouns, especially surnames, titles, and roles, sometimes near government, sports, or dragon-related terms

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     &___
    -0.71
    Autoritní
    -0.69
    complexType
    -0.68
    AndEndTag
    -0.68
    PreferredItem
    -0.63
     lenker
    -0.61
    __(/*!
    -0.61
     الحره
    -0.60
     getItemCount
    -0.60
     дописавши
    -0.60
    POSITIVE LOGITS
     vroeger
    0.52
    Xna
    0.49
     novamente
    0.48
     déjà
    0.48
     Gründer
    0.48
     igjen
    0.47
     reinstated
    0.47
     SME
    0.47
     throwback
    0.47
     Spital
    0.46
    Activations Density 0.346%

    No Known Activations