© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 19675
    Prev
    Next
    INDEX
    Explanations

    meaningful or impactful phrasing

    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_15_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
    stånd
    0.57
    íd
    0.55
    orphism
    0.54
    ipi
    0.53
    ter
    0.51
    idey
    0.50
    readable
    0.49
    ührung
    0.49
    ロ
    0.49
    ίκ
    0.48
    POSITIVE LOGITS
     elegance
    0.49
    Euph
    0.48
    ელის
    0.47
     receb
    0.47
     nectar
    0.47
     absurdity
    0.47
     alert
    0.47
     absurd
    0.46
     imageUrl
    0.46
     tinct
    0.45
    Activations Density 0.038%

    No Known Activations