© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 44-GEMMASCOPE-2-TRANSCODER-262K
    7. 3420
    Prev
    Next
    INDEX
    Explanations

    press

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_44_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
    蓁
    0.45
    ikai
    0.37
    кура
    0.37
     foule
    0.37
     પહોંચ
    0.35
     kos
    0.34
    বিষ
    0.34
    anya
    0.34
     pung
    0.34
     Adonis
    0.34
    POSITIVE LOGITS
     nhá
    0.47
    ดัน
    0.47
    鈕
    0.44
     кнопку
    0.44
     releases
    0.43
     conferences
    0.43
     клави
    0.41
    sure
    0.41
     Releases
    0.41
     pause
    0.40
    Activations Density 0.022%

    No Known Activations