© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 257157
    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_22_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
    единен
    0.44
    야
    0.43
     описа
    0.42
    ᓐ
    0.40
    Hallo
    0.40
    Greg
    0.39
    
    0.39
     остальных
    0.38
     ایم
    0.38
    仯
    0.38
    POSITIVE LOGITS
    freien
    0.51
    fertigt
    0.45
    aprendizaje
    0.44
    énés
    0.43
    altung
    0.42
    ନ୍ତ
    0.42
     rosas
    0.42
     ferv
    0.41
     divorced
    0.41
    boxylate
    0.41
    Activations Density 0.000%

    No Known Activations