© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 19-GEMMASCOPE-TRANSCODER-16K
    7. 7825
    Prev
    Next
    INDEX
    Explanations

    auxiliary verbs "do", "does", "did", "have", and "are"

    oai_token-act-pair · gemini-2.0-flash

    do

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     did
    -1.58
     does
    -1.54
     do
    -1.38
    did
    -1.37
    does
    -1.28
    Did
    -1.24
     DID
    -1.22
     Does
    -1.20
    Does
    -1.20
     Did
    -1.19
    POSITIVE LOGITS
    躇
    0.71
    ITECT
    0.59
    OfDay
    0.58
    WithEmail
    0.57
     invokingState
    0.56
    ILON
    0.56
    ESTIC
    0.55
    inguém
    0.55
    libft
    0.54
    onnaise
    0.54
    Activations Density 0.326%

    No Known Activations