© 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. 10178
    Prev
    Next
    INDEX
    Explanations

    mathematical and code variables

    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
    علي
    0.40
     খাওয়া
    0.40
     calculadora
    0.38
     빼
    0.38
    unden
    0.37
    퍽
    0.37
     trí
    0.36
    ënten
    0.36
    ಿಸಬಹುದು
    0.36
    áticamente
    0.36
    POSITIVE LOGITS
    gest
    0.39
     gest
    0.38
     reject
    0.38
     broadcast
    0.38
     Reject
    0.37
     Act
    0.37
    Reject
    0.37
     Jest
    0.36
    共
    0.36
    ૬
    0.36
    Activations Density 0.030%

    No Known Activations