© 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. 5273
    Prev
    Next
    INDEX
    Explanations

    questions

    oai_token-act-pair · gemini-2.0-flash

    the word "Why"

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

    why

    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
    IntoConstraints
    -0.85
     contextLoads
    -0.82
    Personensuche
    -0.71
     виправивши
    -0.71
     they
    -0.71
    ValueStyle
    -0.71
    AccessorTable
    -0.66
    BeginInit
    -0.66
     @"/
    -0.65
    хьтан
    -0.64
    POSITIVE LOGITS
     للمعارف
    0.57
     don
    0.56
     cuáles
    0.55
     cuál
    0.54
     μην
    0.51
    picas
    0.50
     anzeigen
    0.48
    FromNib
    0.47
     cannot
    0.46
    صدار
    0.46
    Activations Density 0.295%

    No Known Activations