© 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
    2. Gemma-2-2B
    3. 12-GEMMASCOPE-TRANSCODER-16K
    4. 9848
    Prev
    Next
    INDEX
    Explanations

    the words "of", "in", "the", "to" or "on" in combination with the words "future", "history", "search", "like", "his", "facing, modern" or "efficient"

    oai_token-act-pair · gemini-2.0-flash

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     myſelf
    -0.61
    BagLayout
    -0.60
     auffi
    -0.60
    ężczy
    -0.57
     Efq
    -0.57
     poff
    -0.55
    hoy
    -0.54
     Cypri
    -0.53
     rospy
    -0.53
    BeginContext
    -0.52
    POSITIVE LOGITS
     lenker
    0.69
     “
    0.52
    zarchiwizowane
    0.50
    AnchorTagHelper
    0.46
     }{
    0.45
    っこう
    0.45
    bein
    0.44
    iverr
    0.44
     منهم
    0.43
    *]
    0.43
    Activations Density 0.624%

    No Known Activations