© 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. 19515
    Prev
    Next
    INDEX
    Explanations

    water containers

    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
    Not in Any Lists

    No Comments

    Negative Logits
     preprocess
    0.61
     çant
    0.59
     Passengers
    0.59
     Travel
    0.58
     deline
    0.56
     c
    0.55
     ;
    0.55
     여행
    0.54
     Airlines
    0.54
     parasite
    0.54
    POSITIVE LOGITS
    Rash
    0.55
    Rein
    0.51
    Okno
    0.50
    Shall
    0.49
    aza
    0.48
    mild
    0.48
    natur
    0.47
    Rain
    0.46
    Tambah
    0.46
    asen
    0.46
    Activations Density 0.010%

    No Known Activations