© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 237176
    Prev
    Next
    INDEX
    Explanations

    media

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
     ceramic
    0.39
    刹
    0.39
    គ្ន
    0.38
     землі
    0.38
     संख्याओं
    0.37
     cerámica
    0.37
     земли
    0.37
     eligibility
    0.36
     ceramics
    0.36
     chemical
    0.36
    POSITIVE LOGITS
    benhav
    0.42
    樟
    0.41
     Rudolf
    0.40
     Twe
    0.39
    media
    0.39
     Her
    0.39
     Blob
    0.38
    媒体
    0.38
     Losses
    0.37
     Rais
    0.37
    Activations Density 0.000%

    No Known Activations