© 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. 15427
    Prev
    Next
    INDEX
    Explanations

    words related to supplementary content for movies, especially physical media releases

    oai_token-act-pair · gemini-2.0-flash

    whitespace and punctuation

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

    DVD/Blu-ray releases and reviews

    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
    StoryboardSegue
    -1.20
    ValueStyle
    -1.16
     myſelf
    -1.15
     itſelf
    -1.13
    RenderAtEndOf
    -1.13
     themſelves
    -1.10
    yntaxException
    -1.10
    Rhestr
    -1.09
     AssemblyCulture
    -1.08
     himſelf
    -1.06
    POSITIVE LOGITS
     
    0.53
      
    0.49
     J
    0.48
     "
    0.48
    <u>
    0.47
    ↵↵
    0.46
     “
    0.46
    /
    0.46
    ,
    0.46
     be
    0.45
    Activations Density 1.860%

    No Known Activations