© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 9472
    Prev
    Next
    INDEX
    Explanations

    the word "regular" and words that are similar in meaning

    oai_token-act-pair · gemini-2.0-flash

    regular

    np_max-act · gemini-2.0-flash

    regular

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     
    -1.72
     a
    -1.39
    <eos>
    -1.35
    ↵↵
    -1.34
     (
    -1.30
    ↵
    -1.27
    ,
    -1.24
     the
    -1.23
     in
    -1.12
      
    -1.11
    POSITIVE LOGITS
     Efq
    2.28
     Theſe
    2.22
     itſelf
    2.17
     myſelf
    2.16
     Jefus
    2.16
    ^(@)
    2.06
     pleaſure
    2.05
     Monfieur
    2.05
     $_"
    2.03
     Majefty
    2.03
    Activations Density 2.306%

    No Known Activations