© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 30317
    Prev
    Next
    INDEX
    Explanations

    flaky, flag, flirting, flour, flattering

    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_31_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
     emf
    0.41
     EMT
    0.39
     cocoa
    0.38
     EMF
    0.38
    timetable
    0.38
     Lug
    0.37
    𒊺
    0.35
    Thai
    0.35
     gliding
    0.35
    귤
    0.35
    POSITIVE LOGITS
     Fl
    0.87
     फ्ल
    0.81
     fl
    0.80
     фла
    0.80
     ফ্ল
    0.80
    Fl
    0.69
     Flan
    0.67
    フラ
    0.66
     フラ
    0.63
    fl
    0.61
    Activations Density 0.057%

    No Known Activations