© 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. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 54718
    Prev
    Next
    INDEX
    Explanations

    available in various 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_30_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
    ᆸ
    0.42
    formats
    0.41
     teinte
    0.40
     varying
    0.38
    udan
    0.37
    ěn
    0.37
    templat
    0.36
     Peoria
    0.36
    
    0.36
     ভাষায়
    0.36
    POSITIVE LOGITS
     ess
    0.38
     puk
    0.37
    ètres
    0.36
     skul
    0.36
     omt
    0.36
    वों
    0.36
     overhe
    0.36
     Manipulation
    0.35
     revol
    0.34
    Headers
    0.33
    Activations Density 0.003%

    No Known Activations