© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 149688
    Prev
    Next
    INDEX
    Explanations

    en

    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_60_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
    ’
    0.44
     Enzo
    0.41
     zirconium
    0.39
     Piaget
    0.39
     Lagrange
    0.38
    Roh
    0.38
     Zayn
    0.38
    阠
    0.37
     Poirot
    0.36
     Immunohist
    0.36
    POSITIVE LOGITS
    c
    0.48
    se
    0.46
    tal
    0.42
    tap
    0.42
    tum
    0.41
    tick
    0.41
    t
    0.41
    tra
    0.40
    turb
    0.40
    tik
    0.39
    Activations Density 0.000%

    No Known Activations