© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 63993
    Prev
    Next
    INDEX
    Explanations

    say "*"

    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_59_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
    ])/
    0.45
     solves
    0.36
    ('/')
    0.35
     müssen
    0.35
     આવ્યું
    0.35
    ../../
    0.35
     edited
    0.35
     scaled
    0.35
     $\
    0.34
     розмі
    0.34
    POSITIVE LOGITS
     Meters
    0.40
    move
    0.40
    abs
    0.39
     Move
    0.38
    veland
    0.38
    rison
    0.38
    norm
    0.37
    vote
    0.37
     फंक्शन
    0.37
    alignment
    0.37
    Activations Density 0.003%

    No Known Activations