© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 3448
    Prev
    Next
    INDEX
    Explanations

    words that indicate a shift in time or location or a causal connection

    oai_token-act-pair · gemini-2.0-flash

    then

    np_max-act-logits · 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
     then
    -3.16
    then
    -2.61
    Then
    -2.50
     Then
    -2.39
     THEN
    -2.14
     entonces
    -2.13
     então
    -2.03
    THEN
    -1.96
     allora
    -1.80
     dann
    -1.79
    POSITIVE LOGITS
    पया
    0.72
     &___
    0.69
    Legături
    0.69
    ">//
    0.64
     CreateTagHelper
    0.63
    iastes
    0.60
     ujednoznacz
    0.60
    offsetof
    0.59
     EconPapers
    0.58
    withOpacity
    0.57
    Activations Density 6.018%

    No Known Activations