© 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. 2958
    Prev
    Next
    INDEX
    Explanations

    code related to C-style pointer syntax and structure definitions

    oai_token-act-pair · gemini-2.0-flash

    *)

    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
     Theſe
    -1.01
     enfans
    -0.96
     Efq
    -0.94
     Houſe
    -0.91
     religieuses
    -0.90
     becauſe
    -0.90
     Anſ
    -0.89
     HasFactory
    -0.89
     JpaRepository
    -0.89
     supérieurs
    -0.88
    POSITIVE LOGITS
    <bos>
    1.08
    ↵↵
    1.08
    ↵
    0.82
    s
    0.68
    ’
    0.57
    asantry
    0.56
     
    0.56
      
    0.54
     the
    0.54
    etheless
    0.54
    Activations Density 2.348%

    No Known Activations