© 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-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 9163
    Prev
    Next
    INDEX
    Explanations

    time stamps

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_3_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
    ли
    2.55
    𝗯
    2.50
    kaç
    2.22
    ്യ
    2.11
     jambes
    1.97
    𝘃
    1.91
    𝘆
    1.89
     لنا
    1.89
     tapi
    1.87
    𝗹
    1.86
    POSITIVE LOGITS
    ⏲
    2.42
    ﺮ
    2.34
    *}$
    2.30
     Aristotle
    2.30
    ﻂ
    2.27
     iphdr
    2.26
     ERK
    2.26
    '}$
    2.23
     austerity
    2.18
    ){}^
    2.18
    Activations Density 0.033%

    No Known Activations