© 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. 18875
    Prev
    Next
    INDEX
    Explanations

    think of it this way

    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
     bisogna
    0.45
     należy
    0.45
     devemos
    0.41
     phải
    0.40
     dobbiamo
    0.39
    ຕ້ອງ
    0.39
    须
    0.38
     must
    0.38
    PF
    0.38
    須
    0.38
    POSITIVE LOGITS
    Phi
    0.38
     questioning
    0.36
     agendas
    0.35
     laughing
    0.35
     chilling
    0.35
     bpm
    0.35
     phi
    0.34
     desk
    0.34
     past
    0.34
     experiences
    0.34
    Activations Density 0.031%

    No Known Activations