© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 193238
    Prev
    Next
    INDEX
    Explanations

    the request asks for

    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_27_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
     Don
    0.43
     accompanying
    0.40
     Export
    0.40
     Hafen
    0.40
     Deadly
    0.39
     Ihre
    0.38
     parody
    0.38
     p
    0.38
     Delta
    0.38
     Anal
    0.38
    POSITIVE LOGITS
     COMMUNICATIONS
    0.43
     özellik
    0.41
     işlemler
    0.40
     spacerItem
    0.40
     substituir
    0.38
    activité
    0.38
    Fried
    0.38
    िलासपुर
    0.38
    έρ
    0.37
     மாதிர
    0.37
    Activations Density 0.016%

    No Known Activations