© 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-3-27B-IT
    5. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 46427
    Prev
    Next
    INDEX
    Explanations

    US patent

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_22_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    invariant
    0.46
    úr
    0.45
    compact
    0.43
    scissors
    0.43
    ****",
    0.43
    protos
    0.43
    achev
    0.43
    nú
    0.42
    data
    0.42
    experiments
    0.42
    POSITIVE LOGITS
     Th
    0.50
    を選
    0.44
     alltid
    0.44
     ಆಯ್
    0.43
    选
    0.43
    淆
    0.42
    熔
    0.42
     ৩৭
    0.42
    餵
    0.41
     알고
    0.41
    Activations Density 0.001%

    No Known Activations