© 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. 15485
    Prev
    Next
    INDEX
    Explanations

    descriptions of what can be seen with the eye, or how easily something can be seen

    oai_token-act-pair · gemini-2.0-flash

    observation/seeing

    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
    ГЛА
    -0.64
    idazole
    -0.63
    ISTA
    -0.59
     self
    -0.58
    ISTO
    -0.57
     percep
    -0.56
    leger
    -0.55
    IDAE
    -0.55
    yste
    -0.54
     discer
    -0.54
    POSITIVE LOGITS
    postIndex
    0.66
    хьтан
    0.63
     pinulongan
    0.60
    kháu
    0.56
     الرياضيه
    0.55
    fromnode
    0.54
     незавершена
    0.54
    localctx
    0.53
     protoimpl
    0.51
    sizeCache
    0.50
    Activations Density 1.313%

    No Known Activations