© 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. 40717
    Prev
    Next
    INDEX
    Explanations

    uncle, generation, or mother's relations

    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
    ی
    0.71
    s
    0.65
     قریب
    0.65
     którzy
    0.61
     którą
    0.59
     gyda
    0.59
     квіт
    0.59
    </h2>
    0.58
     قوانین
    0.57
     които
    0.56
    POSITIVE LOGITS
    し
    0.91
    в
    0.86
    보
    0.72
    set
    0.70
    ل
    0.70
    سلام
    0.69
    abilir
    0.69
    可
    0.69
    ного
    0.68
     Mahm
    0.68
    Activations Density 0.010%

    No Known Activations