© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 10399
    Prev
    Next
    INDEX
    Explanations

    computer code syntax and related terms

    oai_token-act-pair · gemini-2.0-flash

    Batal

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     ujednoznacz
    -0.85
    rungsseite
    -0.80
    resave
    -0.74
    .)}
    -0.71
    السكان
    -0.71
     >=",
    -0.71
    %)$
    -0.68
    Espèce
    -0.68
    expandindo
    -0.68
    rrggbb
    -0.66
    POSITIVE LOGITS
     argparse
    0.53
    Chi
    0.50
     emp
    0.47
     bu
    0.47
    Ch
    0.46
     Ch
    0.46
     Brust
    0.44
     CommonModule
    0.43
     Corso
    0.43
     b
    0.43
    Activations Density 6.486%

    No Known Activations