© 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. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 181280
    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_24_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
     Algebraic
    0.42
     skulls
    0.42
    鵰
    0.41
     가지고
    0.41
     brains
    0.40
    씻
    0.40
    墮
    0.40
     લાવ
    0.40
     encephal
    0.39
     inexplicable
    0.39
    POSITIVE LOGITS
     cose
    0.44
     depender
    0.38
     intr
    0.37
    <u>
    0.37
    /
    0.36
    ن
    0.36
    ते
    0.35
    Philip
    0.35
     relied
    0.35
     resonate
    0.35
    Activations Density 0.000%

    No Known Activations