© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 136041
    Prev
    Next
    INDEX
    Explanations

    astronomical objects

    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_12_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
     ≤
    0.47
     sql
    0.46
     отсутствии
    0.44
     aristocratic
    0.44
     synthase
    0.44
     ሌ
    0.44
     observational
    0.44
     ………………………………..
    0.44
     airspace
    0.43
     <=
    0.43
    POSITIVE LOGITS
    \
    0.62
    För
    0.55
    Für
    0.54
    inda
    0.51
    ä
    0.51
     för
    0.50
    ll
    0.50
     wichtiger
    0.50
    Meine
    0.48
    Pepper
    0.48
    Activations Density 0.001%

    No Known Activations