© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 40614
    Prev
    Next
    INDEX
    Explanations

    overleaf.com editor

    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_3_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
    0.86
    0.72
    )
    0.72
    ğini
    0.71
    ]
    0.71
    fang
    0.66
     undivided
    0.66
    ab
    0.66
     overall
    0.66
    .
    0.65
    POSITIVE LOGITS
    ت
    0.96
    t
    0.93
    IL
    0.92
    ۔
    0.89
    は
    0.84
    ט
    0.83
    是
    0.78
    А
    0.78
    는
    0.77
    та
    0.77
    Activations Density 0.002%

    No Known Activations