© 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. 13246
    Prev
    Next
    INDEX
    Explanations

    code-related keywords such as 'variable', 'transfer', 'node', 'for', and 'const'

    oai_token-act-pair · gemini-2.0-flash

    coding variable transfer

    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
    Not in Any Lists

    No Comments

    Negative Logits
     Shakspeare
    -1.16
     Efq
    -1.09
     Houſe
    -1.06
     Shaksp
    -1.03
     ―――――
    -0.98
    بوابة
    -0.98
    Portale
    -0.96
     Jefus
    -0.93
     Theſe
    -0.93
     houſe
    -0.90
    POSITIVE LOGITS
     his
    0.61
     so
    0.54
     the
    0.52
     het
    0.51
     Z
    0.51
    0.51
     met
    0.51
    .
    0.50
    l
    0.50
    ­
    0.50
    Activations Density 1.513%

    No Known Activations