© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 11745
    Prev
    Next
    INDEX
    Explanations

    transitions or turning points in a narrative, especially moments of emotional realization or significant events.

    oai_token-act-pair · gemini-2.0-flash

    forms of the word 'compose'

    np_token-act-pair-logits · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     Tetrahedron
    -0.53
     développé
    -0.52
     hvert
    -0.50
     industriels
    -0.50
     fallu
    -0.50
    anus
    -0.50
    laration
    -0.49
    kuuta
    -0.49
     communs
    -0.48
    HasAnnotation
    -0.48
    POSITIVE LOGITS
     collected
    0.71
     composed
    0.68
    GraphicsUnit
    0.64
     Composed
    0.62
     متعلقه
    0.61
    Personendaten
    0.59
     collect
    0.58
     compose
    0.56
     compos
    0.55
    poel
    0.55
    Activations Density 1.169%

    No Known Activations