© 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. 200045
    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_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
     fielded
    0.46
    伱
    0.43
     overrated
    0.43
     ಈಗಾಗಲೇ
    0.42
     😏
    0.42
     타입을
    0.41
     insistent
    0.40
    類的
    0.40
    ժ
    0.40
     mortgages
    0.40
    POSITIVE LOGITS
     ü
    0.44
     z
    0.38
     cât
    0.38
     öpp
    0.38
    多少
    0.37
    C
    0.37
    polo
    0.36
    est
    0.35
     Opening
    0.35
    conven
    0.35
    Activations Density 0.000%

    No Known Activations