© 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. 215074
    Prev
    Next
    INDEX
    Explanations

    package contents

    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
     gada
    0.43
     comet
    0.40
    iksi
    0.39
     baggage
    0.37
     deque
    0.36
     வலு
    0.36
    ogén
    0.36
     keuze
    0.34
    į
    0.34
    甶
    0.34
    POSITIVE LOGITS
     Doug
    0.43
    Doug
    0.41
     особенно
    0.38
     Katie
    0.38
     paralys
    0.38
     Compare
    0.37
     altitudes
    0.37
     vacancies
    0.36
     Supreme
    0.34
     AuthService
    0.34
    Activations Density 0.000%

    No Known Activations