© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 48726
    Prev
    Next
    INDEX
    Explanations

    model training

    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_55_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    鈈
    0.42
     ರೆ
    0.39
     MBC
    0.39
    ൪
    0.39
     gall
    0.38
    categor
    0.38
    adda
    0.37
    Stein
    0.37
    ṯ
    0.37
     categor
    0.36
    POSITIVE LOGITS
     instruction
    0.64
     Instruction
    0.57
     extensively
    0.56
    instruction
    0.50
    produced
    0.49
     created
    0.49
     produced
    0.48
    指令
    0.45
     Created
    0.45
     thoroughly
    0.43
    Activations Density 0.023%

    No Known Activations