© 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. 12350
    Prev
    Next
    INDEX
    Explanations

    references to visual media such as videos and pictures

    oai_token-act-pair · gemini-2.0-flash

    words related to showing or displaying

    np_token-act-pair-logits · gpt-4o-mini

    show

    np_max-act-logits · gemini-2.0-flash
    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
    UnknownFieldSet
    -0.60
    transQ
    -0.53
     незавершена
    -0.52
    Hochspringen
    -0.51
    saurus
    -0.51
    []{"
    -0.51
     kaynağından
    -0.49
     geométrico
    -0.49
    ttin
    -0.49
    rungsseite
    -0.48
    POSITIVE LOGITS
     showing
    2.06
     show
    2.05
     shows
    2.03
     Shows
    1.80
     showed
    1.78
    shows
    1.75
    show
    1.74
     Show
    1.73
    showing
    1.72
     Showing
    1.70
    Activations Density 2.540%

    No Known Activations