© 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. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 102788
    Prev
    Next
    INDEX
    Explanations

    whose + noun

    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_14_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
     ,
    0.46
    essing
    0.44
    enhance
    0.44
    、“
    0.43
    emitting
    0.43
    ,\
    0.43
     Enhance
    0.40
    ,~
    0.40
     -"
    0.39
     I
    0.39
    POSITIVE LOGITS
    Zawodnik
    0.53
    າດ
    0.50
    Karena
    0.48
    atakan
    0.44
    ായക
    0.43
    сын
    0.42
     persones
    0.41
     seter
    0.41
     selector
    0.41
     anum
    0.41
    Activations Density 0.002%

    No Known Activations