© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 47027
    Prev
    Next
    INDEX
    Explanations

    paywalls and membership access

    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_13_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
     komp
    0.52
    струк
    0.50
     besk
    0.50
     koment
    0.49
     usk
    0.49
     amm
    0.48
     hoofd
    0.48
    集
    0.48
     integ
    0.47
    ைகளைக்
    0.47
    POSITIVE LOGITS
    𝗲
    0.57
    edad
    0.56
     depriving
    0.52
    vamos
    0.51
    age
    0.50
     clientèle
    0.50
     ی
    0.50
     willpower
    0.49
     வரலா
    0.49
     Needham
    0.48
    Activations Density 0.045%

    No Known Activations