© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 15443
    Prev
    Next
    INDEX
    Explanations

    first person pronouns followed by auxiliary verbs or "to"

    oai_token-act-pair · gemini-2.0-flash

    ve

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     itſelf
    -0.98
     himſelf
    -0.97
     myſelf
    -0.95
     Anſ
    -0.94
     Majefty
    -0.93
     Theſe
    -0.89
     Jefus
    -0.89
     themſelves
    -0.88
     виправивши
    -0.86
     سكانية
    -0.86
    POSITIVE LOGITS
     loved
    0.39
     g
    0.38
     represented
    0.37
     jelent
    0.35
     known
    0.34
              
    0.34
     attacked
    0.34
    τη
    0.34
     pecho
    0.34
     charged
    0.33
    Activations Density 2.599%

    No Known Activations