© 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. 44-GEMMASCOPE-2-TRANSCODER-262K
    7. 7027
    Prev
    Next
    INDEX
    Explanations

    improvisation

    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_44_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
     flagging
    0.39
    umbu
    0.38
    鋁
    0.37
    urança
    0.36
    என்
    0.35
    atov
    0.35
    ালা
    0.35
     పాఠ
    0.35
     rez
    0.34
    늑
    0.34
    POSITIVE LOGITS
    isation
    0.67
    izations
    0.66
    化的
    0.66
    ization
    0.65
    ised
    0.65
    izacji
    0.62
    化
    0.61
    isations
    0.58
    IZATION
    0.57
     hóa
    0.55
    Activations Density 0.003%

    No Known Activations