© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 63602
    Prev
    Next
    INDEX
    Explanations

    infrastructure formation

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ||
    0.38
    __|
    0.38
    ﻛ
    0.38
    |
    0.38
     narr
    0.36
    river
    0.36
     neoclassical
    0.36
    zoeken
    0.36
    |\
    0.35
    pawns
    0.35
    POSITIVE LOGITS
     içi
    0.39
    azadas
    0.38
     Dawn
    0.37
    겠다
    0.37
     Shi
    0.36
    吮
    0.35
    insi
    0.35
     shi
    0.35
     Mutter
    0.35
     Gee
    0.34
    Activations Density 0.002%

    No Known Activations