© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 15709
    Prev
    Next
    INDEX
    Explanations

    computer code formatting and symbols along with variable and function names

    oai_token-act-pair · gemini-2.0-flash

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    bootstrapcdn
    -0.58
    DOCTYPE
    -0.52
     DAF
    -0.49
    spesies
    -0.48
    género
    -0.48
     actionPerformed
    -0.47
     Ceramby
    -0.46
    إن
    -0.46
     TimeUnit
    -0.46
    jsdelivr
    -0.45
    POSITIVE LOGITS
     GenerationType
    0.66
     ProtoMessage
    0.65
    ecma
    0.62
     HasFactory
    0.60
    oa̍t
    0.60
     censiti
    0.58
    ohistochemical
    0.58
     Италијани
    0.58
    ⤹
    0.57
    NameInMap
    0.57
    Activations Density 40.888%

    No Known Activations