© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 3790
    Prev
    Next
    INDEX
    Explanations

    jargon related to the World of Warcraft (WoW) video game

    oai_token-act-pair · gemini-2.0-flash

    code/level/class/frequencies

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/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.18.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     صوتيه
    -0.79
     Regeneration
    -0.62
     فريبيس
    -0.59
     regenerate
    -0.59
    matitis
    -0.58
    RegressionTest
    -0.57
     regeneration
    -0.56
    anoke
    -0.56
     skill
    -0.52
    برا
    -0.52
    POSITIVE LOGITS
     defaultstate
    0.66
     defStyleAttr
    0.57
     ProtoMessage
    0.54
     invokingState
    0.50
    ThroughAttribute
    0.49
    AppMethodBeat
    0.49
    டை
    0.47
     EClass
    0.47
     htons
    0.47
    CodeAttribute
    0.46
    Activations Density 0.659%

    No Known Activations