© 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. 8004
    Prev
    Next
    INDEX
    Explanations

    words describing crystal and floral scents, as well as scientific terms related to drugs and biology

    oai_token-act-pair · gemini-2.0-flash

    iris

    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
    )$/,
    -0.57
    adaptiveStyles
    -0.56
    ESSOR
    -0.56
    !("{
    -0.54
    glio
    -0.52
     CURIAM
    -0.52
    sopp
    -0.51
    ฏ
    -0.51
    lungen
    -0.51
    llary
    -0.49
    POSITIVE LOGITS
     насељу
    0.79
    Viited
    0.57
    المراجع
    0.56
     initComponents
    0.52
    مراجع
    0.52
    interopRequire
    0.50
    ftagPool
    0.49
    phosa
    0.48
    Lähteet
    0.47
    SequentialGroup
    0.46
    Activations Density 0.456%

    No Known Activations