© 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. 145655
    Prev
    Next
    INDEX
    Explanations

    code structure

    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
    nested
    0.41
     CM
    0.38
     McCormick
    0.38
     Beckman
    0.38
    topping
    0.38
    aus
    0.37
    \},
    0.37
     Dickson
    0.36
    >}
    0.36
    yed
    0.36
    POSITIVE LOGITS
    主的
    0.43
    Pred
    0.42
     누구
    0.42
    ônio
    0.38
     suministro
    0.38
    ittää
    0.36
    Основные
    0.36
     coração
    0.35
     गुरू
    0.35
    ígeno
    0.35
    Activations Density 0.001%

    No Known Activations