© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 10325
    Prev
    Next
    INDEX
    Explanations

    nouns related to health, deliveries, events and religion

    oai_token-act-pair · gemini-2.0-flash

    proximity

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    Istorija
    -0.55
     ujednoznacz
    -0.52
     skole
    -0.52
    feira
    -0.49
     betweenstory
    -0.48
     Савез
    -0.48
    andExpect
    -0.46
     Sequelize
    -0.44
    Clik
    -0.43
     skolen
    -0.42
    POSITIVE LOGITS
     near
    2.41
     Near
    2.20
    near
    2.20
    Near
    2.20
     NEAR
    2.00
    NEAR
    1.74
     nearest
    1.70
     près
    1.55
     nearer
    1.51
     nearby
    1.43
    Activations Density 0.667%

    No Known Activations