© 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
    2. Gemma-2-2B
    3. 0-GEMMASCOPE-TRANSCODER-16K
    4. 6518
    Prev
    Next
    INDEX
    Explanations

    the word "normally" and related adverbs, and, possibly, words related to requirements

    oai_token-act-pair · gemini-2.0-flash

    normally

    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
    MLLoader
    -1.36
     AssemblyCulture
    -1.27
     الرياضيه
    -1.24
    InjectAttribute
    -1.19
    rungsseite
    -1.17
    ImageContext
    -1.17
     utafitiHapana
    -1.11
    HostException
    -1.08
    contentLoaded
    -1.07
    __':
    
    -1.07
    POSITIVE LOGITS
     gratuitas
    0.68
     attiva
    0.66
     antichi
    0.65
     automatiques
    0.65
     enfans
    0.65
     communs
    0.64
     modernas
    0.62
     actuelles
    0.62
     before
    0.61
     boucles
    0.61
    Activations Density 0.799%

    No Known Activations