© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 11240
    Prev
    Next
    INDEX
    Explanations

    positive statements about emotions, recipes and life

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     infatti
    -0.52
     anzi
    -0.50
     ferons
    -0.48
     tuttavia
    -0.47
     veux
    -0.46
     apapun
    -0.45
    Weblinks
    -0.45
     feit
    -0.45
     kuitenkin
    -0.45
     Перейти
    -0.45
    POSITIVE LOGITS
     really
    3.31
    really
    3.05
     Really
    2.84
    Really
    2.81
     REALLY
    2.31
     realy
    1.96
     realmente
    1.86
     wirklich
    1.84
     vraiment
    1.84
     naprawdę
    1.66
    Activations Density 4.464%

    No Known Activations