© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 35013
    Prev
    Next
    INDEX
    Explanations

    punctuations and foreign script

    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_11_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
     magnets
    0.65
    ᱖
    0.65
    ᱓
    0.61
     enduring
    0.61
     accolades
    0.61
     ordinal
    0.61
     herramient
    0.58
     emboss
    0.58
     layering
    0.58
     intrad
    0.58
    POSITIVE LOGITS
    T
    0.64
    ți
    0.62
     Punishment
    0.59
    B
    0.58
    ică
    0.58
    قی
    0.57
     After
    0.57
    M
    0.56
    নায়
    0.55
    }}$
    0.54
    Activations Density 0.020%

    No Known Activations