© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 170257
    Prev
    Next
    INDEX
    Explanations

    obsessions and compulsions

    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_20_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
    㕩
    0.48
     Raceway
    0.47
     faire
    0.46
     Ability
    0.45
     البي
    0.45
     คลิ
    0.45
     సౌ
    0.45
     רבי
    0.44
     mange
    0.44
     Argument
    0.44
    POSITIVE LOGITS
     hemodynamic
    0.44
     asylum
    0.41
    <0x80>
    0.41
     chronic
    0.41
     fragments
    0.40
    "},
    0.40
     asymptomatic
    0.40
     fragmented
    0.40
     anastom
    0.39
     beneficiaries
    0.39
    Activations Density 0.002%

    No Known Activations