© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 170272
    Prev
    Next
    INDEX
    Explanations

    last names often followed by first names

    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_20_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
    card
    0.27
    on
    0.27
    constant
    0.26
    im
    0.25
     after
    0.25
     After
    0.25
    advert
    0.24
    after
    0.24
     aftermath
    0.24
    q
    0.24
    POSITIVE LOGITS
     అయిన
    0.25
    ᖓ
    0.25
    LPTMR
    0.25
     încep
    0.24
     بات
    0.24
    кратно
    0.24
    ptides
    0.24
    ิด
    0.24
    ()[
    0.23
     চাঁদ
    0.23
    Activations Density 0.000%

    No Known Activations