© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 14726
    Prev
    Next
    INDEX
    Explanations

    the word "instruction" and related words

    oai_token-act-pair · gemini-2.0-flash

    instruction

    np_max-act · gemini-2.0-flash
    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
    Not in Any Lists

    No Comments

    Negative Logits
     kasarigan
    -0.77
    asInstanceOf
    -0.70
     Efq
    -0.69
     którzy
    -0.65
    Pratique
    -0.62
     genoux
    -0.62
     flesta
    -0.61
    ^(@)
    -0.60
    выше
    -0.60
     ]
    -0.60
    POSITIVE LOGITS
     Vrbo
    0.70
     <
    0.61
    出版年
    0.60
    uride
    0.60
     nahilalakip
    0.60
     оригіналу
    0.60
    __":
    0.60
     arro
    0.59
     rhetor
    0.59
    ்ட
    0.59
    Activations Density 1.765%

    No Known Activations