© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 7630
    Prev
    Next
    INDEX
    Explanations

    Okay, introducing explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_39_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
    iint
    0.42
     നടത്ത
    0.39
    ┈┈
    0.38
     ministra
    0.38
    Isra
    0.37
    ITAS
    0.37
    짖
    0.35
    министра
    0.35
     toho
    0.34
     существо
    0.34
    POSITIVE LOGITS
     Break
    0.41
     Diving
    0.39
     Documentation
    0.39
     Ocean
    0.38
     Dive
    0.38
     Breakdown
    0.37
    学
    0.37
    ác
    0.36
     County
    0.36
     Oed
    0.36
    Activations Density 0.119%

    No Known Activations