© 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. 19592
    Prev
    Next
    INDEX
    Explanations

    less, headless, dark

    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
     aprob
    0.28
    Можно
    0.25
     Wo
    0.25
     Girl
    0.24
    罗
    0.24
     arbitrator
    0.24
     Льво
    0.23
     gioc
    0.23
     bajo
    0.23
    eiro
    0.23
    POSITIVE LOGITS
    áš
    0.25
    demos
    0.24
    ící
    0.24
    *:
    0.23
    GH
    0.23
    \}.
    0.23
     togetherness
    0.23
    quí
    0.23
     cà
    0.22
    VPN
    0.22
    Activations Density 0.051%

    No Known Activations