© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 134023
    Prev
    Next
    INDEX
    Explanations

    memorable

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_6_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
    ;
    0.97
    ил
    0.93
    지
    0.86
    ای
    0.86
    ;')
    0.83
    आई
    0.82
    고
    0.82
    ﻗ
    0.82
    H
    0.81
    ジ
    0.81
    POSITIVE LOGITS
    recyclerView
    0.86
    to
    0.84
    ens
    0.82
    知道
    0.82
    ü
    0.80
    會
    0.75
     è
    0.74
     اجتما
    0.73
    if
    0.72
     už
    0.72
    Activations Density 0.001%

    No Known Activations