© 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. 35127
    Prev
    Next
    INDEX
    Explanations

    range or relationship of "between"

    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
    ᓚ
    0.57
    ედერ
    0.57
     sün
    0.56
     Bä
    0.53
     सेले
    0.53
    ეგის
    0.53
     On
    0.51
     sclerosis
    0.51
     Fehler
    0.51
    هِ
    0.50
    POSITIVE LOGITS
     foresee
    0.63
     boast
    0.61
    }};
    0.56
     inflict
    0.55
     envisage
    0.54
     insist
    0.53
     limitado
    0.52
    探讨
    0.52
    টাও
    0.51
    to
    0.51
    Activations Density 0.001%

    No Known Activations