© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 224
    Prev
    Next
    INDEX
    Explanations

    words that indicate a legal context and sometimes words that indicate categories or distinctness

    oai_token-act-pair · gemini-2.0-flash

    separate

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     separate
    -2.19
    separate
    -2.00
     Separate
    -1.98
    Separate
    -1.95
     seperate
    -1.87
     SEPAR
    -1.66
     separately
    -1.53
     separado
    -1.37
     terpisah
    -1.34
    Separ
    -1.33
    POSITIVE LOGITS
     AssemblyCulture
    1.01
     مرئيه
    0.91
     CreateTagHelper
    0.83
    antMatchers
    0.83
    XmlAccessType
    0.79
     الحره
    0.75
    MLLoader
    0.75
     Chwiliwch
    0.75
    AndEndTag
    0.74
     виправивши
    0.72
    Activations Density 16.969%

    No Known Activations