© 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. 81344
    Prev
    Next
    INDEX
    Explanations

    list operations and losses

    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
    枼
    0.42
     Да
    0.38
    ໍ່
    0.38
     alen
    0.38
     Pfaff
    0.37
    Авто
    0.37
     Oko
    0.37
     Kia
    0.36
     Mull
    0.35
     Hubert
    0.35
    POSITIVE LOGITS
     Incorporation
    0.44
     epit
    0.42
     incorporation
    0.41
     插
    0.39
     House
    0.39
     house
    0.38
    rice
    0.37
    incorpor
    0.37
     집
    0.36
     incorpora
    0.36
    Activations Density 0.005%

    No Known Activations