© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 221209
    Prev
    Next
    INDEX
    Explanations

    simultaneous, cog, cot

    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_31_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
     تازه
    0.09
     张
    0.08
     Hasan
    0.08
    rypsin
    0.08
    poder
    0.08
    蒟
    0.08
     നടത്തി
    0.08
     ください
    0.08
     _{
    0.08
    淫
    0.08
    POSITIVE LOGITS
     simultaneous
    0.09
    орга
    0.09
     congreg
    0.09
     cog
    0.09
     simult
    0.08
     post
    0.08
     cot
    0.08
    dark
    0.08
     piel
    0.08
     penit
    0.08
    Activations Density 0.001%

    No Known Activations