© 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. 92080
    Prev
    Next
    INDEX
    Explanations

    Félix, Lengyel, Kjellberg, Cat, Flux

    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
    </h2>
    0.76
    n
    0.68
    <0x0D>
    0.61
     العليا
    0.57
    nThe
    0.55
     Umfang
    0.54
    </h4>
    0.54
    },$
    0.54
    </h5>
    0.53
    以此
    0.53
    POSITIVE LOGITS
    ۔
    0.80
    ва
    0.73
    п
    0.70
    ü
    0.70
    ون
    0.69
    ።
    0.67
    í
    0.66
    ə
    0.66
    ches
    0.64
    ж
    0.63
    Activations Density 0.000%

    No Known Activations