© 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. 15729
    Prev
    Next
    INDEX
    Explanations

    Python code related to Django models

    oai_token-act-pair · gemini-2.0-flash

    models

    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
    writeFieldEnd
    -0.72
     kasarigan
    -0.70
    MessageOf
    -0.66
     gynhyrchwyd
    -0.63
    CPtr
    -0.63
     ligiloj
    -0.60
    Tembelea
    -0.60
    ⤹
    -0.56
    脚注の使い方
    -0.56
    :✨
    -0.55
    POSITIVE LOGITS
     IActionResult
    0.54
     arché
    0.44
     dangereux
    0.44
    isDead
    0.42
    ApplicationTests
    0.42
     BrowserModule
    0.40
     skj
    0.40
    lewati
    0.39
     dobrze
    0.39
    omitempty
    0.39
    Activations Density 0.200%

    No Known Activations