© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 7046
    Prev
    Next
    INDEX
    Explanations

    a variety of proper nouns and associated words, including journal references, place names, people's names, and movie titles

    oai_token-act-pair · gemini-2.0-flash

    Initial letters of names

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     myſelf
    -1.95
     purpoſe
    -1.95
     pleaſure
    -1.92
     itſelf
    -1.91
     Majefty
    -1.88
     Jefus
    -1.88
     Monfieur
    -1.81
     Theſe
    -1.80
     themſelves
    -1.80
    ſelf
    -1.76
    POSITIVE LOGITS
     P
    0.77
     Mar
    0.76
     M
    0.74
     C
    0.73
     Br
    0.72
     R
    0.71
     Bra
    0.71
     Ch
    0.70
     K
    0.70
     Bar
    0.69
    Activations Density 1.538%

    No Known Activations