© 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. 161241
    Prev
    Next
    INDEX
    Explanations

    defining options

    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
    Negative Logits
    ങ്കി
    0.37
     "(
    0.37
     folgende
    0.36
    電流
    0.36
    juvant
    0.36
    져
    0.35
     എന്നത്
    0.35
    有些人
    0.35
    &=&
    0.35
     公司
    0.34
    POSITIVE LOGITS
    showthread
    0.37
     irons
    0.36
     கிடைத்த
    0.35
    胖
    0.35
     выше
    0.35
     concealment
    0.35
    符合
    0.35
    mallow
    0.35
     최대한
    0.35
     shot
    0.34
    Activations Density 0.014%

    No Known Activations