© 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. 199689
    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
    Not in Any Lists

    No Comments

    Negative Logits
    yu
    0.39
    Yu
    0.39
    мым
    0.38
    cue
    0.37
    ֖
    0.36
     yu
    0.36
    YU
    0.36
    unier
    0.36
    故
    0.36
    線上
    0.35
    POSITIVE LOGITS
     infrastructures
    0.40
     idiots
    0.40
     bulge
    0.40
     perhaps
    0.39
    واقع
    0.39
     debt
    0.39
     melanoma
    0.38
     dinosaurs
    0.38
     monopolies
    0.37
     refugees
    0.37
    Activations Density 0.000%

    No Known Activations