© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 6722
    Prev
    Next
    INDEX
    Explanations

    Russian and English contrasting phrases

    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_40_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
     atención
    0.40
     ಔ
    0.40
     sublim
    0.39
     subscribe
    0.39
     Subscriber
    0.38
     пунк
    0.38
     prep
    0.37
    ents
    0.37
    Submission
    0.37
     vives
    0.37
    POSITIVE LOGITS
    uszko
    0.40
    崞
    0.37
    マンション
    0.36
     Covent
    0.36
     почвы
    0.36
    ElementString
    0.36
     notched
    0.36
     galaxies
    0.35
     Alka
    0.35
    芑
    0.35
    Activations Density 0.032%

    No Known Activations