© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 193359
    Prev
    Next
    INDEX
    Explanations

    in this view,

    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_27_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
    거나
    0.40
     ಪ್ರ
    0.39
    但这
    0.39
    ]]
    0.38
     அல்லது
    0.38
     অথবা
    0.37
     ಅಥವಾ
    0.37
    ২
    0.37
     किंवा
    0.36
    与其
    0.36
    POSITIVE LOGITS
     membranes
    0.47
     sacro
    0.44
    ."-
    0.41
     medicine
    0.41
     penit
    0.40
     decedent
    0.38
     subjekt
    0.38
     stimuli
    0.38
     tilts
    0.38
     ballast
    0.38
    Activations Density 0.000%

    No Known Activations