© 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. 14295
    Prev
    Next
    INDEX
    Explanations

    the word "to", especially when capitalized

    oai_token-act-pair · gemini-2.0-flash

    to

    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
    Negative Logits
    ◄
    -0.61
     Audiodateien
    -0.60
    urlencoded
    -0.59
     To
    -0.58
     Se
    -0.56
     van
    -0.56
     Sie
    -0.54
     se
    -0.54
     va
    -0.53
     Bis
    -0.52
    POSITIVE LOGITS
    oa̍t
    0.77
    principalTable
    0.73
    IndentedString
    0.63
     @"/
    0.62
     pomeriggio
    0.62
     GenerationType
    0.57
    fjspx
    0.55
     мәкал
    0.54
    StoryboardSegue
    0.54
    tagHelperRunner
    0.53
    Activations Density 1.154%

    No Known Activations