© 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. 3181
    Prev
    Next
    INDEX
    Explanations

    the word 'of'

    oai_token-act-pair · gemini-2.0-flash

    of

    np_max-act · gemini-2.0-flash
    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
    Negative Logits
    ^(@)
    -1.17
     ―――――
    -1.16
    ChildScrollView
    -1.16
     Theſe
    -1.12
     Efq
    -1.12
     doubtnut
    -1.11
     简谱
    -1.08
     iſt
    -1.06
    StoryboardSegue
    -1.05
    EndContext
    -1.05
    POSITIVE LOGITS
     
    0.98
     #
    0.87
     "
    0.82
     the
    0.81
    ↵
    0.79
      
    0.74
    1
    0.68
    ,
    0.68
     -
    0.68
    <bos>
    0.66
    Activations Density 1.514%

    No Known Activations