© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 52774
    Prev
    Next
    INDEX
    Explanations

    lazy loading, code splitting, memoization

    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_30_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
     Englishmen
    0.41
    厉
    0.41
     ranking
    0.40
     faç
    0.38
     monumental
    0.38
     petitioners
    0.38
     societal
    0.38
     armband
    0.37
    ">→</
    0.36
     creators
    0.36
    POSITIVE LOGITS
    hedge
    0.38
    VIT
    0.37
     হওয়ায়
    0.37
    片
    0.36
    神奇
    0.36
     அதிசயம்
    0.36
    HUB
    0.35
     تاکہ
    0.35
     Тро
    0.35
    abbit
    0.34
    Activations Density 0.000%

    No Known Activations