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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 9984
    Prev
    Next
    INDEX
    Explanations

    words, phrases, and syntax commonly found in computer code

    oai_token-act-pair · gemini-2.0-flash

    programming code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     myſelf
    -1.02
     CreateTagHelper
    -0.97
    +#+#
    -0.96
    ValueStyle
    -0.90
     iſt
    -0.89
     houſe
    -0.88
     itſelf
    -0.86
    CppMethod
    -0.85
    Хьажоргаш
    -0.85
     ſtate
    -0.85
    POSITIVE LOGITS
     all
    0.56
     Mar
    0.51
     er
    0.45
     mar
    0.45
     en
    0.45
     ar
    0.42
     Per
    0.42
    tache
    0.42
     cho
    0.42
     C
    0.41
    Activations Density 11.766%

    No Known Activations