© 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. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 100228
    Prev
    Next
    INDEX
    Explanations

    success/otherwise conditions

    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_14_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
    ﻒ
    0.42
     skl
    0.38
     berk
    0.37
     bygg
    0.37
     heaps
    0.37
    гат
    0.37
    qry
    0.36
     용
    0.36
     akhir
    0.36
    洙
    0.36
    POSITIVE LOGITS
    ischen
    0.42
    ushed
    0.40
    ètes
    0.39
     hanno
    0.37
     deberían
    0.37
    ůli
    0.36
     पीड़ित
    0.35
    ighed
    0.35
    uchten
    0.35
    分离
    0.35
    Activations Density 0.042%

    No Known Activations