© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 10399
    Prev
    Next
    INDEX
    Explanations

    words/phrases that seem to indicate the beginning of a process or plan

    oai_token-act-pair · gemini-2.0-flash

    action words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ValueStyle
    -0.90
    AndEndTag
    -0.66
     démocr
    -0.65
    awtextra
    -0.63
    thâu
    -0.63
     BoxFit
    -0.62
    ']){
    -0.60
     оригіналу
    -0.59
     AssemblyCulture
    -0.59
     propOrder
    -0.59
    POSITIVE LOGITS
     convert
    0.83
     write
    0.80
    write
    0.79
     evaluate
    0.79
     respond
    0.78
     apply
    0.78
    convert
    0.77
     create
    0.77
     raise
    0.77
    atize
    0.76
    Activations Density 16.962%

    No Known Activations