© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 1631
    Prev
    Next
    INDEX
    Explanations

    research paper terminology

    oai_token-act-pair · gemini-2.0-flash

    words related to levels and concentrations

    np_token-act-pair-logits · gpt-4o-mini

    levels

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/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.21.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     uVar
    -0.47
     limone
    -0.47
    ESSOR
    -0.46
     Tos
    -0.45
    #!/
    -0.44
    push
    -0.44
    搖
    -0.44
     Hukum
    -0.43
    XmlAccessType
    -0.43
     cherchés
    -0.43
    POSITIVE LOGITS
     levels
    1.23
    levels
    1.13
     Levels
    1.09
     LEVELS
    1.03
    Levels
    1.00
     secretion
    0.96
     level
    0.94
     LEVEL
    0.85
     Level
    0.83
     concentration
    0.82
    Activations Density 5.074%

    No Known Activations