© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 15509
    Prev
    Next
    INDEX
    Explanations

    C++ code and text describing source code, especially "cout" code

    oai_token-act-pair · gemini-2.0-flash

    C++ code: cout/feet

    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
     itſelf
    -1.67
     myſelf
    -1.63
     Jefus
    -1.60
     Monfieur
    -1.57
     Efq
    -1.56
     themſelves
    -1.53
     ſhe
    -1.51
     pleaſure
    -1.48
     himſelf
    -1.45
     Theſe
    -1.44
    POSITIVE LOGITS
     
    1.31
    <eos>
    0.91
     M
    0.82
     a
    0.79
     $
    0.77
     K
    0.69
     i
    0.65
     D
    0.62
     il
    0.62
     T
    0.61
    Activations Density 0.540%

    No Known Activations