© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 221256
    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_31_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
     intros
    0.44
    '][
    0.38
    ucidation
    0.37
    isolate
    0.37
    াদিত
    0.37
     isolate
    0.36
     isolates
    0.35
    成的
    0.34
     berusaha
    0.33
    მდეგ
    0.33
    POSITIVE LOGITS
     Banquet
    0.40
    ಸೆ
    0.40
     Genuine
    0.37
    REF
    0.37
    师
    0.37
    Genuine
    0.36
     Ven
    0.36
    師
    0.36
    િયલ
    0.36
     Conservation
    0.35
    Activations Density 0.000%

    No Known Activations