© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 5490
    Prev
    Next
    INDEX
    Explanations

    code-related keywords and variables, particularly in C++ and Javascript

    oai_token-act-pair · gemini-2.0-flash

    Code/data

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     —
    -0.54
    —
    -0.49
    исленность
    -0.48
    </
    -0.48
    ">)</
    -0.46
     ()
    -0.46
     </
    -0.46
    ()
    -0.46
     CYTHON
    -0.45
    zarchiwizowane
    -0.45
    POSITIVE LOGITS
     Majefty
    0.65
    Autoritní
    0.60
     ↓,
    0.60
     "\<
    0.59
     ་་
    0.59
    AddTagHelper
    0.59
     Anſ
    0.59
     Monfieur
    0.59
     ẞ
    0.57
     Hivatalos
    0.57
    Activations Density 2.428%

    No Known Activations