© 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. 247481
    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
    faits
    0.43
     motivated
    0.39
     Νο
    0.39
     trunk
    0.37
     pl
    0.37
    mstyle
    0.36
     troubled
    0.36
     Ý
    0.36
    Source
    0.36
     suda
    0.36
    POSITIVE LOGITS
    应用
    0.38
    applying
    0.37
    ведений
    0.36
    APPLICATION
    0.35
    ̼
    0.35
    ovenant
    0.35
     ObjectID
    0.35
    зовы
    0.34
    ahiya
    0.34
     લાગ
    0.34
    Activations Density 0.000%

    No Known Activations