© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 62554
    Prev
    Next
    INDEX
    Explanations

    punch above their weight

    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_11_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
    )
    0.59
    s
    0.58
    }
    0.56
     defend
    0.54
     seafood
    0.54
    o
    0.52
    л
    0.51
     substitute
    0.51
     coupé
    0.51
    ]
    0.50
    POSITIVE LOGITS
     എന്നാൽ
    0.59
    Ｈ
    0.59
    matcher
    0.56
    лера
    0.55
    ле
    0.55
     Х
    0.55
    ihydro
    0.55
    و
    0.54
     بالوں
    0.54
     হাসানের
    0.54
    Activations Density 0.001%

    No Known Activations