© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 10226
    Prev
    Next
    INDEX
    Explanations

    words and phrases that indicate changes or movement away from a prior state.

    oai_token-act-pair · gemini-2.0-flash

    away

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     incomplète
    -0.57
    
    -0.52
     ©️
    -0.52
    henswürdigkeiten
    -0.44
    FontStyle
    -0.42
    ScopeManager
    -0.42
     siyang
    -0.41
     Organization
    -0.39
    pierw
    -0.39
     Zink
    -0.38
    POSITIVE LOGITS
     away
    1.35
     Away
    1.15
     AWAY
    1.08
    away
    1.08
    Away
    1.03
    AWAY
    0.98
    aways
    0.94
     runaway
    0.90
     breakaway
    0.87
     escape
    0.85
    Activations Density 1.148%

    No Known Activations