© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 168671
    Prev
    Next
    INDEX
    Explanations

    who shall question

    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_34_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
    ्हे
    0.42
    मला
    0.39
    ᖃ
    0.38
     contrary
    0.36
     সমাধান
    0.36
     graders
    0.36
     reluctantly
    0.36
     lineWidth
    0.36
     frown
    0.36
     scorers
    0.36
    POSITIVE LOGITS
    髄
    0.38
     Massachusetts
    0.34
     έγινε
    0.32
     …
    0.32
    တင်
    0.32
    无
    0.32
    sau
    0.31
     замети
    0.31
     无
    0.31
    vol
    0.31
    Activations Density 0.000%

    No Known Activations