© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 145678
    Prev
    Next
    INDEX
    Explanations

    παρά

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_59_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
    Courses
    0.41
     замети
    0.40
    찡
    0.39
     flagship
    0.38
     сообщил
    0.37
     té
    0.37
     zbyt
    0.37
     wygl
    0.36
    ্সের
    0.36
    ๏
    0.36
    POSITIVE LOGITS
     ap
    0.49
     cele
    0.45
     ty
    0.39
    ো
    0.39
     celebrated
    0.39
     Prism
    0.37
     EMPTY
    0.37
     Ap
    0.36
     ro
    0.36
     steric
    0.36
    Activations Density 0.001%

    No Known Activations