© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 140335
    Prev
    Next
    INDEX
    Explanations

    GT cars, Lucid Air, e-tron

    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_12_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
    𝘈
    0.15
     väx
    0.15
    Ꮡ
    0.14
    ীয়তে
    0.14
    ܀
    0.14
     têm
    0.14
    鹘
    0.13
    深
    0.13
     μετά
    0.13
    毛
    0.13
    POSITIVE LOGITS
    ոն
    0.16
     conceding
    0.15
     conceded
    0.14
    observer
    0.14
    bibitem
    0.13
     deserving
    0.13
    ッジ
    0.13
     গেরিলা
    0.13
     स्ट्रीट
    0.13
    calculated
    0.13
    Activations Density 0.001%

    No Known Activations