© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 7300
    Prev
    Next
    INDEX
    Explanations

    the word "left" in a context suggesting something was omitted or left behind.

    oai_token-act-pair · gemini-2.0-flash

    things being left

    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
    Negative Logits
    IContainer
    -0.69
     Cæsar
    -0.65
    stdafx
    -0.64
     renforcé
    -0.62
     photolibrary
    -0.61
     judicia
    -0.61
     avoient
    -0.61
     '\\;'
    -0.59
    writeFieldEnd
    -0.58
     initComponents
    -0.57
    POSITIVE LOGITS
     ivelany
    0.46
    Халык
    0.43
    WEBPACK
    0.42
    ául
    0.40
    Pozri
    0.40
     intptr
    0.39
    nthetic
    0.39
    Unnamed
    0.38
     ile
    0.38
    Izvori
    0.37
    Activations Density 3.245%

    No Known Activations