© 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. 121651
    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
     fraî
    0.41
    ]))
    0.39
    طب
    0.39
     moderation
    0.39
    राण
    0.39
    ösen
    0.39
    ční
    0.38
     Sule
    0.38
     gần
    0.38
     près
    0.37
    POSITIVE LOGITS
    分别
    0.35
     disconnected
    0.34
     interrupting
    0.34
     zaj
    0.33
    드로
    0.33
     sottop
    0.33
     deprive
    0.33
    旌
    0.33
    扳
    0.33
     வன
    0.32
    Activations Density 0.000%

    No Known Activations