© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 2512
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_40_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
     nakk
    0.40
     Alto
    0.39
     определяет
    0.37
     toolkit
    0.36
    Alto
    0.36
     Dwar
    0.35
    Alb
    0.35
     اوم
    0.34
     -=
    0.34
    unek
    0.34
    POSITIVE LOGITS
     Mundial
    0.44
     hesitant
    0.40
    obic
    0.40
    誹
    0.38
     dropped
    0.38
     MCM
    0.37
    즈
    0.36
     engines
    0.35
     syst
    0.34
     먼
    0.34
    Activations Density 0.018%

    No Known Activations