© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 216808
    Prev
    Next
    INDEX
    Explanations

    statistics

    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_50_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
    én
    0.72
    ÉN
    0.72
    èn
    0.70
     É
    0.51
    éns
    0.51
    ेन
    0.50
    É
    0.49
    ден
    0.48
    ﻦ
    0.48
    en
    0.47
    POSITIVE LOGITS
    stats
    0.41
    Stats
    0.41
    VB
    0.38
     stats
    0.38
    abouts
    0.37
    ab
    0.37
     abz
    0.37
    Ricardo
    0.36
    keits
    0.36
     plumber
    0.36
    Activations Density 0.001%

    No Known Activations