© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 233067
    Prev
    Next
    INDEX
    Explanations

    velero, veloz, megaloblastic, Veluwe

    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_6_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
    мента
    0.53
    ۳
    0.51
    ang
    0.50
    ۲
    0.49
     відповідно
    0.49
    are
    0.49
    elt
    0.49
    ளில்
    0.49
    gunaan
    0.47
    endian
    0.46
    POSITIVE LOGITS
     ICE
    0.66
     H
    0.64
     REI
    0.63
    w
    0.62
     DREAM
    0.61
     DICE
    0.61
     X
    0.60
    كس
    0.60
     L
    0.59
     chiffres
    0.59
    Activations Density 0.000%

    No Known Activations