© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-GEMMASCOPE-TRANSCODER-16K
    7. 12560
    Prev
    Next
    INDEX
    Explanations

    proper nouns of Finnish and Estonian places, people, and establishments

    oai_token-act-pair · gemini-2.0-flash

    Finnish history and language

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     conto
    -0.46
    bmod
    -0.43
    detectChanges
    -0.42
     daz
    -0.42
    usz
    -0.41
     tắt
    -0.41
    asiun
    -0.40
    henswürdigkeiten
    -0.40
    stdafx
    -0.40
     }));
    -0.40
    POSITIVE LOGITS
    脚注の使い方
    0.72
    ValueStyle
    0.70
     savages
    0.65
     Finnish
    0.64
     Finland
    0.61
     Estonian
    0.59
     الرياضيه
    0.57
    Viitteet
    0.57
     betweenstory
    0.56
     eel
    0.56
    Activations Density 0.805%

    No Known Activations