© 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. 47163
    Prev
    Next
    INDEX
    Explanations

    history buffs

    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
    ’
    0.78
    ip
    0.71
    ij
    0.67
    )’
    0.67
    aj
    0.63
    uk
    0.60
    ARA
    0.58
     Ι
    0.58
    는
    0.58
    ){
    0.57
    POSITIVE LOGITS
    في
    0.66
     发表
    0.64
    ků
    0.63
    ל
    0.63
    くない
    0.63
     blancs
    0.63
    вості
    0.62
    غير
    0.62
    шен
    0.61
     sigui
    0.61
    Activations Density 0.001%

    No Known Activations