© 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. 13936
    Prev
    Next
    INDEX
    Explanations

    HTML tags or code snippets which refer to a location and things that pass through it or it could be finding the word "via".

    oai_token-act-pair · gemini-2.0-flash

    via

    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
     
    -1.27
     “
    -1.02
    ↵
    -1.01
     com
    -0.98
     a
    -0.92
     n
    -0.92
     r
    -0.91
     the
    -0.91
     "
    -0.90
     con
    -0.88
    POSITIVE LOGITS
     Efq
    1.91
     itſelf
    1.80
     Monfieur
    1.80
     myſelf
    1.79
     Majefty
    1.73
     Houſe
    1.65
     Anſ
    1.62
    تقاوى
    1.62
     ainfi
    1.59
     themſelves
    1.58
    Activations Density 3.682%

    No Known Activations