© 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. 3982
    Prev
    Next
    INDEX
    Explanations

    Cyrillic script

    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
    adz
    0.38
    liability
    0.37
     Agile
    0.33
    pper
    0.33
    途
    0.33
     Comp
    0.32
     comp
    0.32
     mugs
    0.32
    逼
    0.32
     realises
    0.32
    POSITIVE LOGITS
    Ђ
    0.46
    Њ
    0.45
    Ⲏ
    0.40
    ᄌ
    0.39
     јо
    0.39
    Х
    0.39
     В
    0.39
     І
    0.39
    పోయే
    0.38
    ционер
    0.37
    Activations Density 0.002%

    No Known Activations